Software Engineering
UNBIND: UNlearning By INference-time Directional Steering for Code LLMs
Zhengyang Shan, Jiayun Xin, Yanjun Lin et al. (+7 more)
Code large
language models acquire programming capabilities from large code corpora, but can also memorize implementations that later require removal. Code unlearning is needed to control their continued reproduction when copyright or security concerns arise. However, targeted and retained code share computational patterns, creating a tension between forgetting specific implementations and preserving general programming ability. We propose UNBIND, a code unlearning framework that separately considers which hidden states correspond to the target code and how to suppress its reproduction. By constructing separate directions for these objectives, UNBIND achieves selective unlearning at inference time while keeping model weights fixed. Our evaluation covers fourteen baselines across two code models and two corpora. UNBIND achieves the highest joint forgetting and utility score in every setting. It reduces target code reproduction by 97.3% to 99.1% as measured by F-BLEU, with at most two fewer HumanEval+ and six fewer MBPP+ problems solved than the original models. In repeated extraction tests under a fixed budget, the number of targets yielding exact spans of at least 50
tokens falls from 188–262 to 0–2 out of 300 per setting. No extracted span reaches 100
tokens, and the mean best recovery ratio ranges from 0.43% to 6.45%.
Multilingual and related-code evaluations further show effective forgetting with limited impact on useful programming capabilities, supporting UNBIND as a practical approach to selective code unlearning.
Read the full abstract ▾
All authors Zhengyang Shan, Jiayun Xin, Yanjun Lin, Xu Qian, Zhiang Liu, Minghui Xu, Yue Zhang, Qin Hu, Kun Li, Xiuzhen Cheng
Cryptography and Security
MMSkillRisk: Can Agents Stay Safe When Multimodal Skills Become Traps?
Lingqi Jiang, Jialuo Chen, Jianan Ma et al. (+8 more)
Agent skills are shareable packages of procedural instructions, tools, and examples.
Multimodal skills additionally include visual references that
agents retrieve and inspect during execution. Because these images guide actions, attackers can disguise malicious instructions as ordinary visual guidance within otherwise legitimate skills. Existing skill-security research primarily examines text-carried attacks or scanner detection, leaving the runtime effects of image-borne attacks insufficiently evaluated. We introduce MMSkillRisk, to our knowledge the first publicly available
benchmark dedicated to end-to-end safety evaluation of image-borne attacks in
multimodal skills. To instantiate this attack surface, we design Native-Context Visual Attack (NCVA), which disguises malicious instructions as native components of teaching images, such as annotations and interface labels. The accompanying SKILL.md provides auxiliary guidance toward relevant visual regions without explicitly stating the malicious operation. Built from 28 curated clean skills, MMSkillRisk contains 36 attack packages and 108 executable cases spanning five attack objectives, with separate checks for attack success and legitimate-task completion. Across nine model-harness configurations evaluated in isolated sandboxes, NCVA induces unauthorized operations in every configuration. Its pooled attack success rate (ASR) reaches 43.1%, exceeding the matched text-carrier baseline by 16.4 percentage points, with higher ASR in all nine configurations. Attack success and legitimate-task completion co-occur in 36.5% of cases, reaching 72.2% for GPT-5.6-sol with Codex. These results show that skill-bundled images can induce unauthorized actions even as
agents complete legitimate tasks, so task success alone does not establish safe skill use. Our code and data are available at https://github.com/kaill-jlq/MMSkillRisk.
Read the full abstract ▾
All authors Lingqi Jiang, Jialuo Chen, Jianan Ma, Xinhao Deng, Xiaohu Du, Sibo Yi, Yuqi Qing, Zhenguang Liu, Qinming He, Shiwen Cui, Changhua Men
Machine Learning
Learn Now, Use Next, Trust Later: Prequential Test-Time Learning for LLM Agents
Tong Zhao, Reed Li, Yuyang Hu et al. (+5 more)
Adapting large
language model
agents during deployment requires not only retaining past experience, but also turning new observations into timely guidance. Many test-time learning methods, however, acquire knowledge from completed episodes. Feedback from an ongoing interaction may therefore not be distilled into knowledge soon enough to help the next decision. Acquiring knowledge at the granularity of individual transitions could reduce this delay, but raises a separate challenge: a rule that is useful within one episode may not be reliable enough to guide future episodes. Waiting for validation can forfeit immediate benefits, whereas unrestricted reuse can propagate accidental or misattributed guidance. We introduce StepLearn, a nonparametric framework that separates immediate use from persistent trust. It turns informative transitions into hypotheses that can guide the next step, while requiring prospective validation before reuse across episodes. Their predicted effects are checked against subsequent observations outside the source episodes, and only sufficiently supported hypotheses become available for persistent guidance. This process updates external knowledge while keeping all model parameters fixed. Over five rounds on WebArena-Lite and ALFWorld, StepLearn achieves average success rates of 59.9% and 84.0% with GPT-5-mini, and 57.8% and 88.1% with Qwen3.5-35B-A3B, respectively. It outperforms EvoTest, the strongest baseline, by 2.2-12.7 percentage points across the four settings. Learning dynamics further shows that these gains are not restricted to the final repetition, with advantages already present on first task attempts in most settings.
Read the full abstract ▾
All authors Tong Zhao, Reed Li, Yuyang Hu, Yutao Zhu, Haijin Liang, Haibo Shi, Yu Lu, Zhicheng Dou
Machine Learning
The Decision Value of Perception Compute
Hoang Pham Cong and Ho Viet Duc Luong
Adaptive perception spends extra computation on inputs where perception is expected to improve. When perception feeds a downstream decision system, a better perception output need not produce a better decision. We define the decision value of perception compute as the change in downstream loss from escalating an input from a cheap to an expensive perception mode. Because this value can be negative, the allocation of perception compute should be judged against a budget-constrained decision oracle, with uniform full-fidelity inference as a baseline rather than an upper bound. We introduce DEEP (Decision Evaluation for Escalated Perception), a
benchmark that scores pre-escalation allocators against this oracle under selection, latency and energy budgets, charging each allocator for its own computation. With deployed
monocular geometry on KITTI and nuScenes, we find that 34–54% of the escalations that change downstream loss make it worse; harmful escalations also occur for the published PDM-Closed planner, evaluated open-loop on nuPlan with real detector outcomes. On nuScenes, perception-level gain frequently disagrees in sign with decision value. This mismatch has practical consequences: choosing among fixed deployable signals by missed-object perception gain rather than by decision value reduces realized test decision gain by 7.4% of the all-cheap loss on average. Learned allocators recover part of the oracle's value by finding beneficial escalations but select nearly as much harm as random, and once their own computation is charged at a 20% latency budget, only the lightweight routers, at about 3.5% of a full detector pass, still beat random.
Read the full abstract ▾
Cryptography and Security
Cheap to Hypothesize, Costly to Verify: The Defense Surface of Agentic Vulnerability Discovery
Kaikai Zhang, Zihan Zhang, Yuchong Xie et al. (+4 more)
Autonomous LLM
agents turn vulnerability discovery into a repository-scale search: they generate many vulnerability hypotheses but can verify only a subset under a finite budget. We show that autonomous vulnerability discovery exhibits a hypothesis-verification asymmetry, where verifying a candidate hypothesis through reachability analysis, execution, and proof-of-concept construction is substantially more expensive than forming it. Under a finite resource budget, this makes autonomous discovery a resource-bounded selective-verification process, further exposing verification effort as a unique defense surface. We present RedHerring, which inserts certifiably safe decoys that divert verification effort from real vulnerabilities. Each decoy combines a CVE-derived vulnerability chain that attracts verification with a false bridge that keeps its dangerous sink unreachable. A private certificate lets the defender verify this property efficiently, while establishing the same fact from the released repository requires solving a computationally hard problem. RedHerring further adapts each decoy to the target repository so that it reads as ordinary program logic. Across 33 OSS-Fuzz projects, 70 evaluation instances, and five models under matched budgets, RedHerring reduces real vulnerabilities discovered by 38.7-60.4%. Trajectory analysis shows that
agents spend 30.6-51.5% of completion
tokens and an estimated 32.5-49.9% of runtime verifying decoys, showing that RedHerring redirects a substantial fraction of the fixed search budget toward decoys. When explicitly informed that decoys may be present, the
agent adapts its search strategy, yet RedHerring still reduces vulnerabilities discovered by 37.2% relative to an informed Baseline, showing that its effectiveness does not depend on decoy secrecy.
Read the full abstract ▾
All authors Kaikai Zhang, Zihan Zhang, Yuchong Xie, Zesen Liu, Shuangjie Yao, Zhixiang Zhang, Dongdong She
Cryptography and Security
Similarity Is Not Validity: Defending LLM Semantic Caches Against Poisoning
Zihan Zhang, Shuangjie Yao, Zesen Liu et al. (+8 more)
Semantic caches reduce LLM serving costs by reusing previously generated answers for semantically similar queries. However,
retrieval is based solely on
embedding similarity between the incoming query and cached queries. This design enables cache poisoning: an attacker can cache a malicious response under a query with high cosine similarity to benign requests. The vulnerability stems from a gap between
retrieval similarity and answer validity. From an information-bottleneck perspective, query
embeddings can lose information needed to distinguish valid from invalid cache hits, which limits any matching
algorithm that uses only these
embeddings. We propose a novel defense that recovers this necessary information from the raw text of the cache key. Across poisoning attacks,
adversarial queries share a rewrite-residual structure: they pair a rewrite of the target query with residual content. The rewrite maintains high similarity, while the residual elicits the malicious response. Deleting the residual makes the remaining rewrite more similar to the incoming query. We exploit this structure using Deletion Gain to search shortened variants of the cached query for similarity gains, and an Answer Check to test whether the removed text contributes to the stored answer. We prove that Deletion Gain stays positive when a deletion leaves text close enough to the rewrite, and we search for such deletions with a sliding window. Across three poisoning attack classes, our defense blocks 82.0% to 98.2% of poisoned entries at a 5% false-positive rate, with negligible serving overhead.
Read the full abstract ▾
All authors Zihan Zhang, Shuangjie Yao, Zesen Liu, Zhixiang Zhang, Wai Ip Lai, Dung Hiu Hilton Yeung, Chun Kit Zhang, Fuchen Ma, Yuanyuan Yuan, Yu Jiang, Dongdong She
Information Theory
Dual-Branch Vector-Quantization-Aided Satellite Digital Semantic Communication with Index Compression for High-Resolution RSI Over AFDM
Jianqiao Chen, Nan Ma, Xiaodong Xu et al. (+7 more)
High-resolution remote sensing imagery (RSI) transmission is constrained by satellite-ground bandwidth and channel impairments, yet existing methods struggle to simultaneously achieve extreme compression and robust transmission. To address this, we propose a dual-branch vector-quantization aided satellite digital semantic communication (DVQ-SDSC) framework for RSI transmission over affine frequency division multiplexing (AFDM), whose bandwidth savings arise from two interrelated aspects. First, at the source-coding level, a dual-branch framework is developed to unify deep joint semantic coding, VQ-aided index transmission, channel estimation and adaption in an end-to-end architecture; departing from symmetric encoder designs, the codec is recast as an asymmetric dual-branch architecture that separately processes the high-frequency residuals and the low-frequency structural semantics, with gated fusion and channel-adaptive reconstruction jointly restoring the semantic content. Second, at the index-coding level, we develop a principal component analysis (PCA)-aided codebook reordering to align index
topology with latent correlations, and devise group differential pulse-code modulation (G-DPCM) to encode prediction residuals rather than absolute indices, lowering the index bitrate while locally isolating clipping and channel errors. A two-stage training strategy further decouples channel impairments from the semantic codec. FAIR1M experiments over 3GPP NTN-TDL-D demonstrate that DVQ-SDSC with G-DPCM index coding outperforms the conventional JPEG-LDPC scheme at the base rate of 0.0625 bits per pixel (BPP), and that G-DPCM applies directly to the trained codec without retraining, yielding additional index compression at no extra cost.
Read the full abstract ▾
All authors Jianqiao Chen, Nan Ma, Xiaodong Xu, Tingting Zhu, Huishi Song, Chen Dong, Rui Meng, Wenkai Liu, Ke Peng, Ping Zhang
Information Retrieval
Structured Interaction, Visual Localization, and Robust Execution for Complex Web Tasks: A Technical Report on the WebRetriever Challenge
Ziqi Zhang, Shaohui Li and Bing Li
This report presents the web
agent system developed for the WebRetriever Challenge. The system follows a structuredinteraction- first strategy, using semantic webpage information for routine browser operations and invoking visual perception only when structured representations are insufficient. Three key designs are introduced: grid-assisted visual localization for difficult-to-access controls, hierarchical context management for reducing redundant page and interaction history, and fault-aware execution mechanisms for stable multi-browser task processing. The system achieved a pass rate of up to 79% in local evaluation on Protocol 1. In the official Protocol 3 competition, it achieved a 59% pass rate with eight concurrent browser workers and ranked first overall, winning the WebRetriever Challenge.
Read the full abstract ▾
Cryptography and Security
Raising the Bar for Chinese Adolescent LLM Safety: A Culturally-Grounded, Fine-Grained Benchmark
Jinxiang Wang, Yifan Liu, Jing Tan et al. (+3 more)
Safety risks in conversations with adolescents are not always explicit. A request may appear harmless unless a model considers the user's age, circumstances, and earlier turns. Existing Chinese safety
benchmarks mainly target general users and give limited
attention to adolescent safety. Single-turn tests also miss risks that emerge over several turns. QH-Bench is a Chinese-
language benchmark for adolescent content safety, with scenarios grounded in Chinese social and cultural settings. The single-turn track contains 715 test items organized into 10 risk domains, 50 subdomains, and 143 fine-grained risk scenarios. The multi-turn track contains 100 four-turn trajectories in a balanced 10-by-10 design that combines the same ten domains with ten cross-turn mechanisms. Both tracks use the same five-level safety-helpfulness scale and automatic judge, with track-specific criteria. Evaluation of 13 open-weight models identifies offline-contact scenarios as a shared weakness. Every model receives negative scores on more than half of the items involving offline meetings with online contacts, unfamiliar groups, and adults. This includes InternLM2.5-20B, the single-turn leader; negative scores indicate responses that partially or clearly facilitate risk. GLM-4-32B, the multi-turn leader, receives negative scores on 60% of complete trajectories in which users build relationships before invoking loyalty or confidentiality. These findings identify two priorities for the evaluated models: handling adolescent offline-contact risks and maintaining safety boundaries under relational pressure. Leading aggregate scores do not establish that these specific weaknesses have been resolved.
Read the full abstract ▾
All authors Jinxiang Wang, Yifan Liu, Jing Tan, Xiangyu Zhao, Xin Yao, Xuetao Wei
Artificial Intelligence · Cross-listed from astro-ph.IM
Reconstructing Implicit Scientific Knowledge: Evaluating LLM Agents through End-to-End Reproduction of Astronomy
Yuehui Wang, Xinyu Qi, Guirong Xue et al. (+4 more)
The integration of large
language models (LLMs) into scientific workflows is accelerating, yet their ability to reconstruct the
reasoning underlying published research remains unexplored. Papers specify explicit procedures while leaving many methodological dependencies-data selection, calibration corrections, priors, and domain assumptions-implicit. This ambiguity complicates the evaluation of LLM-based
agents, since a failure to reproduce a result may reflect either limitations of the
agent or underspecification in the source. We present a framework that evaluates
agents through end-to-end reproduction, separating execution from verification and computational failure from methodological ambiguity. We apply it to fourteen astronomy studies: a case study from The Astrophysical Journal and thirteen papers published in Nature. Eleven of the thirteen contained an ambiguity preventing a uniquely specified reproduction path. In a controlled case study, twelve predefined paths, a 3x2x2 sensitivity analysis over sample definition, sky masking, and parallax zero-point treatment-gave estimates from 2.16 to 3.53 kpc for the same quantity, with only one recovering the published value (about 2.70 kpc). The published value was never used as an optimization target, selection criterion, or stopping condition; the matching path was found only after all twelve had run. Crucially, the decisive information (a +0.02 mas parallax zero-point correction) was already in the paper, but the
agents did not recognize its causal relevance until the analysis made the effect visible. Matching a published outcome therefore does not validate reconstruction of the underlying
reasoning, and the bottleneck is as often a failure to connect relevant information as to retrieve it. End-to-end reproduction thus serves both as a test of reproducibility and as a framework for evaluating implicit scientific knowledge in AI systems.
Read the full abstract ▾
All authors Yuehui Wang, Xinyu Qi, Guirong Xue, Cheng Wang, Yangbin Xie, Xiaoyu Tang, Cong Sun
Computer Vision
FurE: Efficient Instance-Specific 3D Fur Reconstruction without Animal-Fur Datasets
Srinjay Sarkar, Prakhar Kaushik, Soumava Paul et al. (+1 more)
Realistic and editable animal fur reconstruction from multi-view images is challenging due to fine-scale detail, self-occlusion and obfuscation, and, unlike human hair, the lack of animal-fur
datasets. Fur usually covers most of an animal's body, with large inter-species and intra-species variability. We present FurE, an efficient strand-based animal fur reconstruction method that recovers a per-strand, editable groom by optimizing a root-conditioned latent field, decoded into strand geometry via a PCA-based decoder. We reconstruct a defurred animal body using local fur-thickness cues from a surface-constrained Gaussian Frosting representation together with part-based priors. We further show that a PCA-based decoder learned from human-hair strand data can alleviate animal-data scarcity while enabling substantially faster optimization. FurE achieves a 10x speedup in strand training over current SOTA dense per-strand optimization while retaining strand fidelity and generalizing across synthetic and real-world sequences, with quantitative and qualitative validation despite the reduction in training time.
Read the full abstract ▾
All authors Srinjay Sarkar, Prakhar Kaushik, Soumava Paul, Alan Yuille
Computation and Language
Telescopic Language Models
Zhilin Guo, Boqiao Zhang, Hakan Aktas et al. (+14 more)
One deployed
language model must often serve many compute budgets, yet serving each budget still means a separate training or compression run per point. We train a Telescopic
Language Model (TLM) to be that continuum: a nested-capacity
Transformer supervised by
stochastic prefix supervision with a full anchor. At every step, one randomly truncated prefix of the capacity axis is trained against the full next-
token target, alongside one full-capacity pass, so the trained artifact is a valid
language model at every depth. Two forward-backward passes per step, no architectural change, nothing extra at inference. Fixed-exit suites such as Matryoshka
Language Model Suites (MLMS) occupy one point in this design space, and the point has a cost: supervising only a few fixed exits leaves the nested model at chance level everywhere else (perplexity 10^2-10^5 in our baselines). On a 200M proxy suite (20B FineWeb-Edu
tokens, identical data stream for all methods), a single TLM run is a valid
language model at every one of its twenty layer prefixes, in perplexity and on perplexity-sensitive downstream tasks, reducing the area under the quality-budget curve by 43-44% relative to the fixed-exit suites while matching them at full capacity, at ~12% lower GPU cost per run. The prefix sampling density is a dial: concentrating it on a few depths recovers fixed-exit quality there at the price of the continuum, so the operating points become a training-time choice rather than an architectural one. These results indicate that the training objective, not the nesting itself, is what makes a model elastic.
Read the full abstract ▾
All authors Zhilin Guo, Boqiao Zhang, Hakan Aktas, Kyle Fogarty, Nursena Koprucu Aslan, Wenzhao Li, Canberk Baykal, Albert Miao, Siyu Hong, Yixiao Liu, Adam Wu, Ashish Kumar Singh, Sakar Khattar, Chenliang Zhou, Weihao Xia, Cristina Nader Vasconcelos, Cengiz Oztireli
Computer Vision
Zimo Wang, Junkun Yuan, Angtian Wang et al. (+9 more)
Modern
video diffusion models require tens of denoising evaluations over long spatiotemporal
token sequences. Distribution Matching
Distillation (DMD) reduces the number of function evaluations (NFE) to just a few. However, DMD samples can degrade during training, exhibiting progressive oversaturation and artifacts. We trace this instability to critic errors, which enter successive student updates and accumulate over time. We introduce Projected Distribution Matching
Distillation (PDMD) to filter critic errors. PDMD projects out the component of the DMD update parallel to the student-critic endpoint residual. At a fixed noisy query, we prove that this residual is an unbiased estimate of the critic's endpoint error. Under high-dimensional assumptions, this projection removes a constant fraction of critic error while discarding only a vanishing fraction of ideal DMD signal. Empirically, the projection stabilizes training and improves sample quality where DMD degrades and develops unnatural textures. PDMD requires only a one-line code change to DMD, with no extra loss, network, data, model pass, or multi-stage training. With Wan2.1, PDMD achieves a VBench total score of 83.73 at 4 NFE, surpassing matched DMD by 1.03 points. On MiniMax-H3 joint
video-audio generation, PDMD achieves a VideoGen-Eval visual total score of 83.17, 0.41 points above the strongest distilled baseline. PDMD also achieves the best performance on all six audio metrics among the compared 4-NFE models. Qualitative comparisons and user studies favor PDMD over the distilled baselines in visual quality, motion, and audio quality. Code and models are available at https://pdmd2026.github.io/.
Read the full abstract ▾
All authors Zimo Wang, Junkun Yuan, Angtian Wang, Haotian Yang, Canyu Zhang, Siyuan Yuan, Xingchang Huang, Bo Liu, Yizhi Wang, Yiding Yang, Chongyang Ma, Gordon Guocheng Qian
Computer Vision
Learning Native Reflection in Unified Models with Interleaved Reinforcement Learning
Yijia Fan, Ziqi Huang, Zhongang Cai et al. (+5 more)
Unified
multimodal models can both look at and render images, so in principle they can repair their own generations: diagnose what an image gets wrong, revise it, observe the result, and diagnose again. Whether a revision helps is known only after it is rendered, so the reflection text and the image generation must be learned jointly, over the whole loop. Supervised fine-tuning (SFT) on reflection trajectories gives a cold start but does not find the high-success repair paths, and naive RL that optimizes only the renderer or only one head leaves most of the gain untapped. We introduce UMM-Reflection, which applies reinforcement learning (RL) to complete reflection trajectories inside one unified model: sibling trajectories share one initial image, so the group-relative advantage compares reflection strategies, and one trajectory-level advantage updates both the reflection
tokens and the flow-based revisions, avoiding the combinatorial blow-up of per-round credit assignment. Unlike single-round editing or pipelines with an external critic, credit flows across rounds and to both roles of the same model, and no verifier is needed at inference. On BAGEL, UMM-Reflection improves GenEval by 12.05 points over SFT, and the gains transfer to WISE (+10.97), OneIG-Bench (+3.48), and T2I-CompBench++ (+4.63), none of which is used in training.
Read the full abstract ▾
All authors Yijia Fan, Ziqi Huang, Zhongang Cai, Yan Li, Zimo Wen, Wanqi Yin, Haiwen Diao, Ziwei Liu
Computation and Language
Retrieving Biblical Intertextual References in Karen Blixen's Seven Gothic Tales
András Kovács, Alexander Conroy, Daniel Hershcovich et al. (+1 more)
Identifying intertextual references is central to literary scholarship, but computationally difficult when source material is transformed through paraphrase, allusion, historical
language, and translation. We investigate this problem through biblical intertextuality in Karen Blixen's Seven Gothic Tales. Drawing on the commentary to a critical edition, we construct a
benchmark of 189 annotated references and evaluate
retrieval against all 31,170 verses of historically plausible Danish Old and New Testament translations. We compare TF-IDF and BM25 with
multilingual and Danish sentence encoders, examine the effect of linguistic normalization, and fine-tune a Danish encoder using hard negatives and five-fold cross-validation. We analyze performance across automatically derived lexical-overlap strata representing quotations, paraphrases, and allusions. Linguistically normalized BM25 provides a strong zero-shot baseline, attaining an overall R@10 of 0.365 and retrieving every quotation within its ten highest-ranked verses. The best zero-shot dense model achieves a comparable overall score of 0.360 while performing better on allusions. Fine-tuning DFM-large raises its overall R@10 from 0.265 to 0.508 and more than doubles its performance on allusions, from 0.138 to 0.339. However, evaluation against editorial annotations alone understates the model's scholarly usefulness: a literary scholar judged seven of 30 selected rank-one predictions counted as false positives to be meaningful additional references. These findings show both the potential and the epistemic limits of computational intertextual
retrieval. Rather than treating scholarly annotations as exhaustive or model outputs as discoveries, we propose
retrieval models as heuristic co-readers that recover documented references and generate candidates for expert-led close reading.
Read the full abstract ▾
All authors András Kovács, Alexander Conroy, Daniel Hershcovich, Jens Bjerring-Hansen
Computer Vision
Reliability-Gated Fusion of Consumer Head and Foot IMUs for Lower-Body 3D Pose
Zhilin Guo, Boqiao Zhang, Oszkár Urbán et al. (+8 more)
Sparse inertial pose estimation promises camera-free motion capture from consumer devices, but consumer sensors are unreliable: firmware-fused orientations are biased, mounting varies between sessions, and streams drift or drop out. On a new 35-take single-subject
benchmark pairing an earbud head inertial measurement unit (IMU) with two smart-insole foot IMUs (SAM-3D-Body pseudo-ground-truth labels), we show the reliability problem is channel-level: a channel ablation isolates foot acceleration as the most informative input (66.6 mm vs. 79.0 mm head-only) and the firmware-fused foot orientation as the liability that destroys the gain. We therefore let the model learn how much to trust each channel of each stream: one temporal gate per stream per channel block, trained with an auxiliary reliability objective on synthetically corrupted pretraining data. The channel-gated model is the most accurate of our learned fusion arms on clean data (69.4 mm vs. 83.7 static, 86.6 ungated) and under every simulated fault (bias in training; drift, dropout eval-only); its gates suppress the natively biased foot-orientation channels on clean real data without test-time supervision and flag dropout bursts at 0.92-0.999 AUROC. Two contrasts: dropping a channel known a priori to fail is flat across foot faults but collapses when an unanticipated stream fails (head dropout: 92.9 vs. 79.3 mm); and a fine-tuned HMD-Poser is more accurate on clean data (64.4 mm) and nominally under drift, with no significant paired difference under bias or dropout, but a larger worst-case degradation from clean (+16.1 vs. +3.5 mm, single seed). Learning to gate reliability instead of sensor count is the lever for deployable sparse inertial capture. Code is available at https://github.com/ZhilinGuo/reliability-gated-imu-fusion.
Read the full abstract ▾
All authors Zhilin Guo, Boqiao Zhang, Oszkár Urbán, Josef Bengtson, Hakan Aktas, Wenzhao Li, Siyu Hong, Kyle Fogarty, Chenliang Zhou, Ali Senguel, Cengiz Oztireli
Machine Learning
Unifying Distributional Training for One-Step Visual Generation
Chi Zhang, Shi Haoyang, Yueyi Liu et al. (+9 more)
Distributional training provides collective supervision for one-step visual generation by matching real and generated features in frozen representation spaces. We introduce a unified theoretical framework that separates distribution modeling from matching discrepancy and connects global objectives to pointwise feature updates through Wasserstein gradient flow. Under this framework, FD-Loss and Gaussian-kernel Drifting are recovered through Gaussian optimal transport and kernel-density-based KL matching, respectively. The framework motivates MGFlow, which models feature distributions with Gaussian mixtures at an adjustable granularity between global moments and sample-based representations. MGFlow supports both optimal transport and score-based matching, and couples mass-constrained sample assignment with paired component updates to address mode collapse that mixture expressivity alone does not resolve. On ImageNet $256\times256$, MGFlow substantially surpasses the FD-Loss baseline, achieving state-of-the-art results with 1.45 $\mathrm{FDr}^6$ on pMF-H and 1.64 on JiT-H. For text-to-image generation, MGFlow post-trains FLUX.2 [klein] 4B into a one-step generator that outperforms the original four-step model on both GenEval and PickScore.
Read the full abstract ▾
All authors Chi Zhang, Shi Haoyang, Yueyi Liu, Ruichuan An, Junkang Zhou, Chang Li, Xiuyuan Lu, Yichi Zhang, Bo Wang, Yuhang Wu, Sen Cui, Miao Liu
Robotics
DexRoam: Learning Mobile Bimanual Dexterous Manipulation from Egocentric Whole-Body Human Demonstrations
Rui Zhou, Yibo Yuan, Junkai Zhao et al. (+4 more)
Mobile bimanual dexterous manipulation requires continuous coordination of locomotion, whole-body motion, and finger-level dexterity within a single trajectory, creating a severe
robot demonstration bottleneck.
Egocentric human demonstrations offer a scalable alternative, but prior approaches ease the transfer by simplifying human motion, discarding exactly the fine-grained, coupled structure such tasks depend on. We present DexRoam, a complete system for learning mobile bimanual dexterous manipulation from human demonstrations, in which whole-body motion remains continuous and coupled throughout the human-to-
robot transfer process. To enable scalable collection of whole-body human manipulation demonstrations, we develop a tracker-free capture system using only a consumer VR headset and a head-mounted stereo camera, without external cameras or motion trackers. We then perform three explicit
alignment stages—embodiment, action-semantic, and temporal—to map captured motion into the
robot action space, preserving fine-grained whole-body motion and allowing human and
robot demonstrations to be jointly learned by standard VLA policies. Real-world experiments with different VLA backbones show that human demonstrations consistently improve policy learning across training paradigms, raising average success from 29% to 56% on GR00T N1.7 and from 32% to 57% on pi0.5, while matching
robot-only training with half the
robot demonstrations. Ablations confirm that each
alignment stage is necessary. These results highlight the potential of human demonstrations for scalable whole-body mobile manipulation with preserved fine-grained motion structure.
Read the full abstract ▾
All authors Rui Zhou, Yibo Yuan, Junkai Zhao, Fangyuan Zhao, Xiaoguang Zhao, Shanghang Zhang, Sirui Han
Machine Learning
TokenCast: Forecasting Token Consumption During LLM Agent Execution
Chaoqian Ouyang, Ling Yue, Libin Zheng et al. (+7 more)
When a large
language model (LLM)
agent executes the same task,
token consumption can vary by over an order of magnitude across runs. The
agent chooses its next steps based on tool feedback and intermediate results, while the growing context steadily inflates the input size of every subsequent call. The total consumption of a task is therefore hard to predict before execution and the prediction must be revised as the run unfolds. In this paper, we propose TokenCast, which learns a composable cost representation for each execution segment, recording its own consumption and the context growth it introduces. Composing adjacent segments yields a cumulative estimate that captures the extra input cost incurred when context from earlier segments is re-read by every later call. As execution unfolds, newly observed evidence refreshes the forecast, requiring no additional LLM calls and incurring a mean cumulative prediction time of 32.8 ms per run on SWE-bench Verified. Across 4 task suites and 6
agent models, TokenCast's mean absolute error reduction against the strongest comparator averages 14.5% over 96 evaluated combinations. In offline budget-control replay, TokenCast uses 21.3% fewer
tokens on average than a fixed-budget policy at matched trace completion. The code is available at https://github.com/DEFENSE-SEU/TokenCast.
Read the full abstract ▾
All authors Chaoqian Ouyang, Ling Yue, Libin Zheng, Hanghui Guo, Shengxiang Xu, YiShu Wang, Ran Li, Jian Yin, Shaowu Pan, Shimin Di
Computation and Language
Scaling Long-Form Story Generation via Narrative State Tracking
Zhennan Wan and Jianfei Chen
LLMs have demonstrated strong capabilities in creative writing. However, scaling them to full-length novels remains challenging, as maintaining narrative consistency becomes increasingly difficult. Existing story-generation methods typically focus on stories of up to about ten thousand words, leaving their ability to scale to full-length novels underexplored. In this work, we introduce Narrative State Tracking
Agent (NstAgent), a training-free agentic framework that allows LLMs to track a structured narrative state including characters, past events and future requirements. We extend an existing
benchmark to compare narrative consistency across lengths, and use it together with a writing-quality
benchmark to systematically evaluate stories ranging from 10K to 100K words. We show that NstAgent achieves better narrative consistency and writing quality as stories grow longer, and neither of them degrades noticeably as length increases, suggesting that it provides an effective approach to scaling story generation toward full-length novels.
Read the full abstract ▾
Systems and Control
Statistical Learning of Contractive Dynamical Representations for Composite Adaptive Control
Min Kim, José Leonardo Brenes, Fred Hadaegh et al. (+1 more)
We present a representation-learning framework for composite adaptive tracking control under dynamically coupled disturbances. The framework connects classical disturbance-accommodating control (DAC) to recent last-layer adaptive disturbance-rejection methods. Specifically, we introduce a statistically principled hard expectation-maximization (hard-EM) procedure, with a Kalman smoother in the hard E-step, to identify dynamical representations of disturbance whose latent
evolution is uniformly contractive. The learned representation evolves a latent disturbance-excitation state from measured plant features and control inputs and decodes that state into the time-varying disturbance acting on the nominal plant, thereby extending prior "fixed-decay" last-layer adaptive methods to a learned, predictive DAC-style formulation. Combined with
Bayesian filtering of the learned latent state, this representation yields a composite adaptive tracking controller with predictive capability and provable exponential convergence to a bounded neighborhood. We validate our approach experimentally on a slippery ground vehicle carrying a
liquid-sloshing tank and a pendulum load, and we further assess its robustness on a system of coupled Duffing oscillators. Across both settings, the method achieves accurate disturbance prediction and improved overall tracking performance relative to fixed-decay representation-learning ablations, LTI disturbance-accommodating baselines, and model-based PD baselines.
Read the full abstract ▾
All authors Min Kim, José Leonardo Brenes, Fred Hadaegh, Soon-Jo Chung
Machine Learning
Neural Harmonic Measure Operator
Jinjin He, Sinan Wang, Yuchen Sun et al. (+1 more)
We introduce Neural Harmonic Measure Operator (NHMO), a neural solver for
elliptic PDE problems on variable-shape domains. The harmonic measure of a domain is the boundary probability distribution that, integrated against any boundary data, returns the Dirichlet Laplace solution. It depends only on the geometry, not on the boundary data. NHMO parameterizes the density of this measure as a
transformer-based boundary kernel supervised by Walk-on-Spheres exit samples, so one trained kernel handles different boundary values on a shape with no retraining. We extend it to Poisson via a classical decomposition, with an auxiliary network amortizing the source-induced correction and avoiding the singular volume quadrature that breaks direct evaluation. At inference, new boundary values and new sources both yield PDE solutions by re-integration against the fitted kernel and lift, with no retraining. NHMO improves over four prior baselines on the MCB-B 3D variable-shape Poisson
benchmark across all five categories, and is competitive with major neural-operator baselines on a controlled 2D testbed.
Read the full abstract ▾
All authors Jinjin He, Sinan Wang, Yuchen Sun, Bo Zhu
Machine Learning
How to Loop MoE: Flatten the Experts, Untie the Attention
Shouren Wang, Chuang Ma, Mohsen Hariri et al. (+6 more)
Looped
Transformers reuse one block of layers several times: by spending extra computation they push a model of fixed size further, and so use its parameters more fully; while sparse mixture-of-experts (MoE) models activate only a few of many experts for each
token. Looped MoE bridges these two design philosophies and gives MoE models new potential for better expert usage, but it raises a question: how to loop a MoE? We answer it with Foil. With the expert parameters and the expert compute per
token held fixed, Foil (1) flattens the experts, halving the expert layers, doubling the experts per layer and doubling the passes, so that every routing decision chooses from a larger pool, and (2) unties the
attention, giving each pass its own
attention parameters while the experts and routers stay shared. Experiments show that Foil clearly outperforms the unflattened looped baseline: at 20B
tokens every Foil model has lower pretraining loss than the baseline; at 100B
tokens the loss improves monotonically with the degree of flattening, the most flattened Foil ending 0.012 nat below the baseline at equal parameters and compute, with downstream accuracy on par or better; untying the
attention also yields more balanced and more confident routing at equal shape. Our ablations analyse why Foil works and turn the findings into design guidance for looped MoE: the returns of looping and of widening the expert layers amplify each other, routing confidence tracks healthy expert use better than load balance, and a sparse looped MoE should therefore use more experts per layer and more passes. Code and configurations are available at https://github.com/SR-A-W/how-to-loop-moe.
Read the full abstract ▾
All authors Shouren Wang, Chuang Ma, Mohsen Hariri, Debargha Ganguly, Wang Yang, Xiaoqing Tong, Qianying Liu, Xiaotian Han, Vipin Chaudhary
Machine Learning
KV-streams for Efficient Compaction in Agentic Reinforcement Learning
Emiliano Penaloza, Dane Malenfant, Dheeraj Vattikonda et al. (+15 more)
Scaling the horizon of agentic LLMs is bottlenecked by the need to fit ever longer context traces in GPU
memory. Context compaction has been the most popular mechanism to alleviate this issue, keeping GPU
memory constant for a given trace. Unfortunately, most compaction strategies rely on prefilling the LLM context many times over, hindering training throughput. To alleviate this bottleneck and enable efficient trainable compaction, we propose KV-streams, a plug-and-play strategy compatible with any compaction strategy that substantially increases throughput while showing no evidence of hindering performance. KV-streams enable scalable compaction by streaming the KV cache forward rather than flushing it after each compaction. We show that KV-streams enable three different compaction strategies, achieving a 2.6 to 5x wall-clock speedup in training. Beyond efficiency, we find that the streamed KV cache can act as a recurrent state, carrying forward information that has long since disappeared from the context. Specifically, in a controlled setting we show that, contrary to prior work, RL alone is all that is needed for this behavior to emerge. Overall, we show KV-streams to be an efficient and lightweight plug-and-play addition to any post-training pipeline.
Read the full abstract ▾
All authors Emiliano Penaloza, Dane Malenfant, Dheeraj Vattikonda, Roger Creus Castanyer, Siddarth Venkatraman, Abhay Puri, Jonathan Light, Matthew James Sargent, Augustine N. Mavor-Parker, Massimo Caccia, Lucas Caccia, Glen Berseth, Esmeralda S. Whitammer, Alessandro Sordoni, Minseon Kim, Marc-Alexandre Côté, Laurent Charlin, Guillaume Lajoie
Computation and Language
Towards Communication-Efficient Social Intelligence in Language Agents
Linxiao Gong, Yijie Xu, Tianfu Wang et al. (+7 more)
Socially intelligent
language agents must negotiate, coordinate, and resolve conflicting preferences while respecting the time and
attention of both participants. Balancing these demands is challenging because
agents must convey enough to address a partner's constraints and advance their goals without adding words that do not help the interaction. In this paper, we propose Teacher-Assisted Communication Training (TACT) to improve social goal attainment while reducing communication cost, making interactions with
agents more productive and less demanding. We first characterize communication efficiency in terms of action strategy and expression, whose effects extend beyond the current utterance to the partner's response and subsequent exchanges. We design TACT to revise student-generated actions, test the revisions through partner responses, and distill useful feedback into the student. An expression specialist removes unnecessary detail while preserving the intended action, while a strategy specialist proposes alternatives that may better address the partner's constraints. To determine which revision helps, TACT samples a partner response for each candidate and selects a teacher reference by balancing local goal support against action-
token cost. That reference guides on-policy
distillation on the student's own generation prefixes, allowing the student to act independently at deployment. We evaluate TACT on SOTOPIA and AgentSense. On SOTOPIA, it achieves the highest Goal among the evaluated methods on All and Hard while using substantially fewer target
tokens than SFT+SDPO. On AgentSense, it improves goal success over the initial student while reducing target
tokens and interaction messages.
Read the full abstract ▾
All authors Linxiao Gong, Yijie Xu, Tianfu Wang, Yin Wu, Yili Wang, Xingbo Yao, Huizai Yao, Xilin Xia, Haowen Yang, Hui Xiong
Computation and Language
Improving Test-Time Scaling with Adaptive Looped Transformers
Yichen You, Tianyu Fu, Aosong Feng et al. (+4 more)
Looped
transformers have demonstrated promising parameter efficiency by reusing layers for latent computation. Prior studies compare looped and non-looped models at matched parameters or per-
token FLOPs. However, to the best of our knowledge, whether looping improves test-time scaling as outputs grow longer remains underexplored. Through post-training looped
transformers, we study the accuracy-compute slope, measured as the accuracy gain per doubling of test-time decoding FLOPs. We find that existing looped
transformers often yield steeper slopes than their non-looped baseline, yet underperform it at matched compute. While fixed-depth looping spends extra iterations on every
token, our analysis shows that many
tokens do not benefit from extra iterations. We therefore propose TaH2, which enables the model to focus extra iterations on the
tokens that benefit from looping. It jointly post-trains the backbone and an iteration decider through lookahead depth supervision, which uses online labels indicating whether further iteration improves the prediction. TaH2 improves both the efficiency and attainable accuracy of test-time scaling. On challenging AIME
benchmarks, TaH2 improves the accuracy-compute slope by 53% (2.74 vs. 1.79) over the non-looped baseline, exceeding the baseline's peak accuracy by about 3.4 points at matched test-time compute. As the maximum iteration depth increases, existing looped models largely plateau, while TaH2's gain over the non-looped baseline continues to grow from +2.8 points at depth 2 to +3.9 points at depth 8. Our code is available at https://github.com/thu-nics/TaH.
Read the full abstract ▾
All authors Yichen You, Tianyu Fu, Aosong Feng, Xingtai Lv, Xuefei Ning, Ning Ding, Yu Wang
Data Structures and Algorithms
Near-Optimal Bounds for Testing Residual-String Equality and Parenthesis Languages
Hadar Strauss
Residual-String Equality, denoted $\texttt{ResStringEq}$, is the property consisting of all pairs of strings over $\{0,1,*\}$ that are equal after deleting all `$*$' symbols from them. This property was first introduced by Fischer, Magniez, and Starikovskaya (SODA 2018), who used it to show a lower bound on testing the $\texttt{Dyck}$
languages, where $\texttt{Dyck}_m$ is the
language consisting of balanced sequences of parentheses over $m$ parenthesis types. They showed that testing $\texttt{ResStringEq}$ on inputs of length $n$ requires $\Omega(n^{1/5})$ queries, and presented a reduction from testing $\texttt{ResStringEq}$ to testing $\texttt{Dyck}_m$ for any $m \geq 2$. Furthermore, they showed that $\texttt{Dyck}_m$ can be tested with $O(n^{2/5+\delta})$ queries for every constant proximity parameter, where $\delta>0$ is an arbitrarily small constant. In this work, we nearly close the gap, by showing that testing $\texttt{ResStringEq}$, and hence $\texttt{Dyck}_m$ (for any $m\geq 2$), requires $\Omega(n^{2/5})$ queries. We also show a stronger lower bound of $\Omega(\sqrt{n})$ for testers that make non-adaptive queries. We establish that the $\Omega(\sqrt{n})$ bound is nearly tight, by presenting a non-adaptive tester for $\texttt{ResStringEq}$ that uses $O(n^{1/2+\delta})$ queries for an arbitrarily small constant $\delta>0$. Furthermore, we extend this non-adaptive tester to the $\texttt{Dyck}$
languages, with the same query complexity. Finally, we improve the dependence on the proximity parameter $\epsilon$ in the tester of Fischer, Magniez, and Starikovskaya, reducing it from $O(1/\epsilon)^{\mathrm{poly}(1/\delta)}$ to $O(1/\epsilon)^{O(\log(1/\delta))}$.
Read the full abstract ▾
Computer Vision
Copy the Same, Distill the Difference: Initializing Linear Vision Transformers
Huaiyuan Qin, Muli Yang, Gabriel James Goenawan et al. (+9 more)
Linear
Vision Transformers (ViTs) are designed to replace the
attention in Softmax ViTs with the linear-complexity
attention operator for more efficient
token routing, but they require from-scratch pre-training and typically underperform the original Softmax version. How to initialize linear ViTs both efficiently and effectively still remains unclear. In this work, we explicitly ask: given that most foundation ViTs are built on the mainstream Softmax
attention, can linear ViTs benefit from their pre-trained weights? Recent works on
Attention Transfer show that
attention is the effective transferable component between Softmax ViTs, suggesting
attention alone suffices for such reuse. However, we find the opposite for Softmax-to-linear transfer. The
attention weights are operator-specific: copying them barely helps, and is sometimes even worse than random initialization. Instead, the
attention's
token routing behavior can be recovered through
distillation with a proper loss design, letting linear ViTs reduce the gap and even match Softmax ones. In contrast, the MLP weights, which carry the learned representation, are operator-agnostic: they can be transferred by simple direct copying, which already carries most of the benefit of the pre-trained weights. Thus, copying MLPs can serve as an effective foundation for Softmax-to-linear transfer: paired with the distilled
attention, linear ViTs eventually close the remaining gap and even surpass Softmax ones. These findings hold consistently across various linear ViT variants, different model sizes, and diverse
datasets. We hope this study deepens the understanding of reusing pre-trained weights across
attention operators: copy what stays the same and distill what differs, to recover the benefit across the Softmax-to-linear boundary.
Read the full abstract ▾
All authors Huaiyuan Qin, Muli Yang, Gabriel James Goenawan, Shiqi Huang, Min Kass Chong, Wahyu Wiratama, Peng Hu, Chen Gong, Wu Liu, Xi Peng, Chun Jian Ho, Hongyuan Zhu
Artificial Intelligence
FinAutoRubric: Expert-Guided Automatic Rubric Generation for Evaluating Financial Research Agents
Hoyoung Lee, Suyeol Yun, Jack Haverty et al. (+17 more)
Evaluating finance research
agents requires rubrics that reflect expert standards and fix the values correct as of an information cutoff. Expert-reviewed finance
benchmarks rely on fixed, per-item rubrics, which are costly to extend and cannot encode each institution's own standard. In FinAutoRubric, experts specify reusable evaluation guidance, while
agents and code carry out query-specific rubric generation, review, and validation. This expert guidance governs every
agent, as
prompts and as rules that code enforces, and a Task Bank of reusable criteria carries it across tasks. In long-horizon loops that follow the expert guidance, a writer
agent researches every expected value and a reviewer
agent verifies it, and failures escalate to a human. On three expert-authored finance
benchmarks, its rubrics track expert scoring as closely as the strongest evaluated generator while stating the expert rubric's expected value for more criteria, their scores agree with human grading, and in-house analysts prefer them in a blind review. The released 100-query FinAutoRubric
Benchmark, built from in-house analysts' key questions across 78 tasks and eight asset classes, shows that rubrics from an earlier model generation still leave headroom for a later one.
Read the full abstract ▾
All authors Hoyoung Lee, Suyeol Yun, Jack Haverty, Yunju Cho, Meesong Kim, Daekyung Park, Sumin Kim, Jihoon Kwon, Jasmine Jia Geng, Andrew Chin, Yin Luo, Edward Tong, Yu Yu, Zach Golkhou, Minkyu Kim, Igor Halperin, Young Cha, Alejandro Lopez-Lira, Chanyeol Choi, Yongjae Lee
Computer Vision
InfiniHand: Streaming World-Space Hand Motion Estimation from Egocentric Video
Kerui Ren, Kaiwen Song, Weiguang Zhao et al. (+8 more)
World-space hand motion estimation from
egocentric video requires recovering 3D articulated hand geometry while tracking camera egomotion. Existing approaches heavily rely on cascading independent hand pose
estimators and SLAM systems, resulting in error accumulation, complex pipelines, and severe computational overhead. To address these limitations, we present InfiniHand, an end-to-end streaming feed-forward framework that jointly estimates MANO parameters, camera trajectories, and hand locations directly from uncalibrated
egocentric video. InfiniHand integrates persistent spatiotemporal
memory with hand-centered visual features, explicitly coupling camera motion with local hand geometry within a unified architecture. We train InfiniHand in two progressive stages by first learning robust camera-space hand priors and then extending to streaming world-space reconstruction. To support this process, we aggregate a pretraining corpus of approximately 5,000 hours of
egocentric data across multiple public
datasets. Extensive evaluations demonstrate that InfiniHand outperforms state-of-the-art baselines on in-domain
benchmarks, achieving a 21.4% reduction in ARCTIC PA-p compared to ViDiHand while substantially mitigating world-space drift. Furthermore, InfiniHand generalizes robustly to in-the-wild
videos and operates at 11.19 FPS, delivering more than twice the throughput of HaWoR.
Read the full abstract ▾
All authors Kerui Ren, Kaiwen Song, Weiguang Zhao, Yuxi Wang, Yufei Liu, Bo Dai, Haoyu Guo, Chunhua Shen, Mulin Yu, Tao Lu, Junting Dong