Computation and Language
Zero-shot Dependency Parsing with Unsupervised Cross-Lingual Bootstrapping
Lalita Lowphansirikul, Attapol Rutherford, Jian Gang Ngui et al. (+2 more)
Pre-trained
language models (PLMs) with encoder-based architectures have shown impressive capabilities in zero-shot cross-lingual transfer for various
language understanding tasks. However, applying this technique to dependency parsing remains a significant challenge due to its syntactic nature. To boost model generalizability across linguistic typologies, we propose a cross-lingual unsupervised bootstrapping method to improve syntactic knowledge within the PLM. We show that our method achieves a significant improvement in zero-shot parsing performance in low-resource
languages. Analysis of these bootstrapped models uncovers increased robustness in recognizing syntactic structures, evidenced by higher scores in parameter-free tree probing tests.
Read the full abstract ▾
All authors Lalita Lowphansirikul, Attapol Rutherford, Jian Gang Ngui, Sarana Nutanong, Peerat Limkonchotiwat
Computation and Language
How Many Labels Does a Language Need? Annotation Budgets and Cross-Lingual Pooling for African-Language Text Classification
Bhanu Prakash Vangala, Sowmya Guda and Navya Vangala
Every text classifier for an African
language begins with a budgeting question: how many labelled examples are needed, and can labels from other African
languages stand in for them? We answer both questions empirically for 28
language-task pairs, news topic classification in 16
languages (MasakhaNEWS) and tweet sentiment in 12
languages (AfriSenti), using a character n-gram linear model that trains in seconds on two CPU cores with no pretrained weights and no accelerator. Monolingual learning curves at budgets from 25 to several thousand labels show that topic classification reaches 90% of its full-data macro-F1 with about 400 labels in the median
language, while sentiment is still improving at the full training size in 11 of 12
languages and needs thousands of labels. Pooling the full training data of the other
languages in the
benchmark is worth a great deal at small budgets and nothing at large ones: at 25 target labels it adds 0.20 macro-F1 on average for news (up to 0.43 for Lingala) and 0.08 for sentiment, the gain decays to zero by 800 labels, and at full size pooling hurts in 9 of 16 and 8 of 12
languages. Twenty-five target labels plus pooled data match what 100 to 400 monolingual labels achieve for most news
languages. A complete zero-shot transfer
matrix shows that transfer without any target labels recovers a median of only 13% (news) and 4% (sentiment) of the gap between a majority-class predictor and the in-
language model, with the exceptions explained by shared script (Amharic and Tigrinya), shared lexicon (English and Nigerian Pidgin, the Arabic dialects), or a shared label prior rather than by
language family. We release code that regenerates every number from the public
benchmark files and translate the results into concrete annotation guidance for teams building African-
language classifiers without GPUs.
Read the full abstract ▾
Human-Computer Interaction
Fluency Without Evidence: Constraint-First Design and the Limits of Self-Report in AI-Assisted Learning
Fatima T. Zahra, Wei Wang, Frances Harper et al. (+1 more)
A generative AI teaching partner should support
reasoning over supplying conclusions; however, this has not been tested against learning in an authentic course. Drawing on design-based research, we specify the position as a
conjecture map and report a first design cycle in two graduate-level research methods courses. Students used an AI teaching partner employing a constraint-first sequence requiring them to state and justify positions before receiving questions. Pre- and post-measures of AI literacy, critical thinking, and metacognitive awareness were collected alongside interaction records. AI literacy increased, concentrating in understanding AI, whereas critical thinking, awareness, and knowledge did not change. Since changes were limited to self-report measures, they may reflect growth in confidence instead of capacity. Interaction records, meanwhile, showed brief exchanges, uneven enactment of the constraint-first sequence, and missing records. These findings show why AI-supported learning requires interaction records to provide a more defensible basis for AI-supported designs than self-reports.
Read the full abstract ▾
All authors Fatima T. Zahra, Wei Wang, Frances Harper, Jiangen He
Computation and Language
Timur Mudarisov, Mikhail Burtsev and Radu State
How many
tokens from its context does a
language model actually use, and what determines that number? We study this question through self-
attention. Without retraining, we retain only the
tokens with the highest
attention weights at each head, layer, and query, keeping their original weights unchanged. By varying the selected set size and measuring the increase in negative log-likelihood (NLL), we estimate the effective
attention set size needed to stay within a chosen loss tolerance. Relatively small selected sets can keep NLL close to the full-
attention baseline, although the required size varies across models.
Attention-based selection substantially outperforms random selection. Selected sets exhibit
geometric structure, although
geometric separation alone does not establish that model loss is preserved. Extending context while evaluating the same prediction targets increases the required set size, while its fraction of context decreases over the tested range. Experiments with a fixed supporting fact show that additional background pushes its
tokens down the
attention ranking and reduces their
attention mass. Renormalizing the retained weights can substantially reduce the required set size, showing that it also depends on how selected representations are combined. Conditional theoretical models explain how competition and
attention-mass retention can produce growing set sizes without more distinct information to retrieve. These results provide a way to measure effective
attention set size in
language models and investigate its dependence on context, competition, and aggregation.
Read the full abstract ▾
Artificial Intelligence
Co-PiLOT: Constrained Physics-Informed Latent Optimization for Target-Driven Inverse Design
Mahish K. Guru, Mayank Nagar, Ayush vyas et al. (+3 more)
Inverse design of physical systems (molecules, devices, microstructures) often reduces to optimizing a high-dimensional structure against an expensive black-box simulator. Direct search is difficult because the space is non-Euclidean, feasibility is hard to encode, and each evaluation is expensive. We present Co-PiLOT, a latent optimization approach that maps candidates through a generative encoder-decoder, uses the decoder as a learned validity prior, and searches the latent space with physics-informed black-box optimization. The framework is applied on the inverse design of magnesium
alloy microstructure/texture. We develop a
vision transformer based-encoder; paired with latent
diffusion,
diffusion transformer and rectified-flow
transformer-based decoders on $\sim80{,}000$ EBSD-derived microstructure
dataset to learn a minimal bottleneck, $z$. The ViT-FMDiT model ($z$=$768$) reconstructs high-fidelity microstructure images (FID $27.86$, MS-SSIM $0.178$), which our self-segmenting orientation codec converts into input grids for
crystal plasticity solver. Finally, we introduce MERIDIAN, an active latent optimizer driven by deep-kernel Gaussian-process uncertainty, failure-aware feasibility prediction,
manifold-aware trust regions, and target-aware acquisition. Within a budget of $160$ simulations, the ViT-FMDiT and MERIDIAN combination yields the best target-driven objective score, reducing the relative target error by $3$–$22\%$ against seven baselines (DANTE, TuRBO, BAxUS, CMA-ES, DDOM, SEIKO, DDPO) on the same decoder.
Read the full abstract ▾
All authors Mahish K. Guru, Mayank Nagar, Ayush vyas, Jan Bohlen, Roland Aydin, Noomane Ben Khalifa
Computer Vision
EndoPrior-GS: Dynamic Endoscopic Reconstruction with a Joint Texture Prior
Jiaqi Huang, Shidong Wang, Tong Xin et al. (+1 more)
Dynamic endoscopic reconstruction is fundamental to robotic surgery and computer-assisted interventions. While 3D Gaussian Splatting (3DGS) realises real-time rendering, its application to deformable intraoperative environments remains constrained by spurious geometry and varying illuminations. To address these limitations, we introduce EndoPrior-GS, a novel pipeline that explicitly couples frame-extracted
vision heuristics and estimated depth maps. EndoPrior-GS derives a joint texture prior from a tool-filtered valid tissue mask, a non-specular photometric filter, and anatomical structural salience, yielding a probability map that guides primitive initialisation and subsequent density control. The prior is further extended to the temporal domain through a texture-aware term that dynamically weighs pairwise primitive contributions during training. We conduct extensive experiments on
benchmark datasets EndoNeRF and SCARED, and the obtained results show that our method EndoPrior-GS reduces Flow Error by 27.7% and 25.8% over the representative approaches while preserving competitive rendering quality and real-time rendering speed. Our project website is available at https://jiaqi-huang-77.github.io/EndoPrior-GS/.
Read the full abstract ▾
All authors Jiaqi Huang, Shidong Wang, Tong Xin, Kabita Adhikari
Robotics
ExceptionDrive: A Planning-Oriented Counterfactual Corner-Case Benchmark for Autonomous Driving
Ziyi Luo, Zhe Sun, Yehao Lu et al. (+5 more)
Average performance on routine driving
benchmarks does not establish planner reliability under rare, safety-critical hazards. We proposed ExceptionDrive, a counterfactual planning
benchmark that uses VLM-assisted screening, localized multi-view editing, and quality
auditing to insert hazards into real nuScenes scenes while preserving their context. Its 21 tasks span six safety families and define hazard or conflict regions, local safety constraints, and acceptable responses. Because hazard insertion can invalidate the recorded human trajectory, our reference-free protocol evaluates edited predictions using Unsafe Rate (UR), Hazard Clearance Compliance (HCC), Hazard Proximity Response (HPR), and Counterfactual Trajectory Shift (CTS), which measure core-region intrusion, clearance compliance, clearance relative to a prescribed margin, and counterfactual trajectory change. Seven representative planners frequently intrude into hazard regions or provide insufficient clearance. We also develop a Reminder
Agent that, without sample-specific task labels, converts visual evidence and the shared taxonomy into structured records of hazard presence, type, and a recommended high-level strategy. The
agent neither predicts trajectories nor controls the vehicle; its records guide a VLM-based decision
agent. In zero-shot experiments, the reminders improve strategy accuracy and reduce under-warning.
Read the full abstract ▾
All authors Ziyi Luo, Zhe Sun, Yehao Lu, Lei Zhou, Lisheng Wu, Xuewei Li, Zequn Qin, Xi Li
Computer Vision
Learning from synthetic photorealistic raindrop for single image raindrop removal
Zhixiang Hao, Shaodi You, Yu Li et al. (+2 more)
Raindrops adhered to camera lens or windshield are inevitable in rainy scenes and can become an issue for many computer
vision systems such as autonomous driving. Because raindrop appearance is affected by too many parameters, therefore it is unlikely to find an effective model based solution. Learning based methods are also problematic, because traditional learning method cannot properly model the complex appearance. Whereas deep learning method lacks sufficiently large and realistic training data. To solve it, in our work, we propose the first photo-realistic
dataset of synthetic adherent raindrops for training. The rendering is physics based with consideration of the water dynamic,
geometric and photometry. The
dataset contains various types of rainy scenes and particularly the rainy driving scenes. Based on the modeling of raindrop imagery, we introduce a detection network which has the awareness of the raindrop refraction as well as its blurring. Based on that, we propose the removal network that can well recover the image structure. Rigorous experiments demonstrate the state-of-the-art performance of our proposed framework.
Read the full abstract ▾
All authors Zhixiang Hao, Shaodi You, Yu Li, Kunming Li, Feng Lu
Machine Learning
Learning Beyond What You Sample: Off-Policy-Aware Cross-Model Trajectory Exchange for RLVR
Doohyuk Jang, Yoonsik Park, Gyouk Chu et al. (+2 more)
Reinforcement Learning with Verifiable Rewards (RLVR) methods such as GRPO rely on successful self-generated trajectories, but finite rollout budgets can produce all-fail groups with no reward-based policy-gradient signal. While additional rollouts improve the chance of success at higher cost, successful trajectories missing from one model's rollouts may already have been discovered by another. Indeed, we observe that heterogeneous models often succeed on complementary
prompts, creating opportunities for mutual learning without a designated stronger teacher. To exploit this complementarity, we propose GRAFT (Gated Replacement of Answer-Failed groups with peer Trajectories), an off-policy-aware framework that replaces all-fail groups with informative peer groups. GRAFT transfers both successful and unsuccessful peer responses with peer-computed advantages, while controlling cross-model mismatch through sequence-level compatibility weighting and
token-level importance ratio clipping. Across three heterogeneous model pairs and five mathematical
reasoning benchmarks, GRAFT consistently improves both models over GRPO with the same per-model rollout budget, gaining 2.1 points on average and up to 4.5 points in model-level average performance. Stored peer trajectories preserve most of the gains, improving over GRPO by 1.8 points on average without simultaneous co-training.
Read the full abstract ▾
All authors Doohyuk Jang, Yoonsik Park, Gyouk Chu, Sihwan Park, Eunho Yang
Machine Learning
Strict-Saddle Landscapes and Multi-Rank Geometry in Low-Tubal-Rank Tensor Sensing
Eugene Agyei-Kodie, Longxiu Huang, Shuang Li et al. (+1 more)
We study the optimization landscape of low-tubal-rank tensor sensing through a balanced factorization. Under a tubal restricted isometry condition, we establish a quantitative strict-saddle landscape with no spurious local minima for arbitrary
Fourier multi-rank profiles. We further show that the local geometry depends on the
Fourier-slice ranks rather than the tubal rank alone. Uniform ranks yield quadratic growth transverse to the solution orbit, whereas nonuniform ranks produce quartically flat directions through hidden frequency-wise overparameterization, even when the factor width equals the exact tubal rank. Numerical experiments illustrate the global optimization behavior and the contrasting local geometries.
Read the full abstract ▾
All authors Eugene Agyei-Kodie, Longxiu Huang, Shuang Li, Xiao Liang
Software Engineering
AgentBug-Smith: Automatically Reproducing Real-World Harness Bugs in Agentic Systems
Yiming Cheng, Alfin Wijaya Rahardja, Mengshi Zhang et al. (+3 more)
Agent harness bugs exhibit unique characteristics and remain challenging for state-of-the-art software
agents to repair. Progress in this area is further hindered by existing
benchmarks, which contain only a small and fixed number of executable harness bugs while requiring hundreds of human hours to construct. This work presents AgentBug-Smith, an automated harness bug reproduction approach that continuously discovers and reproduces real-world harness bugs from open-source agentic systems. Across different backbone LLMs, AgentBug-Smith consistently outperforms existing bug reproduction techniques designed for general software, achieving 10.67% - 27.56% higher success rates of reproducing harness bugs. By applying AgentBug-Smith to open-source agentic systems in the wild, we construct Live-Harness-Bench, a live and extensible
benchmark that currently contains 200 reproducible harness bugs. We further demonstrate the utility of Live-Harness-Bench through two downstream applications. First, we use Live-Harness-Bench as the evaluation
benchmark to systematically evaluate state-of-the-art software
agents, revealing their limited capabilities in repairing real-world harness bugs. Second, we use Live-Harness-Bench as a knowledge base of real-world harness bug fixes, from which reusable repair skills can be distilled to improve existing software
agents, increasing their harness-bug repair rates by 6.32%. Together, AgentBug-Smith and Live-Harness-Bench establish a scalable foundation for continuously evaluating and improving software
agents on harness bug repair, turning real-world
agent failures into executable evaluation instances and reusable knowledge for harness improvement, thus contributing to the ultimate goal of recursively self-improving
agents.
Read the full abstract ▾
All authors Yiming Cheng, Alfin Wijaya Rahardja, Mengshi Zhang, Zihao Chen, Zhenpeng Chen, Yiling Lou
Computation and Language
It's Not What the Image Shows: Irrelevant Context Destabilises VLM Judges Without Informing Them
Nagham Omar, Mahmoud Jabarin, Kinan Ibraheem et al. (+1 more)
Vision-
language models (VLMs) are increasingly used in place of human annotators, making it important that substitutability tests reflect the model rather than incidental evaluation conditions. We introduce MIST, the Misleading-Image Stress Test: 200 English sentences, each built around a phrase readable either figuratively or literally and shown with an aligned image depicting its reading, a misleading image depicting the opposite, or no image at all. The guidelines require the label to be decided from the sentence alone, so no image should change any answer. We expected each image to pull a judge's labels toward the sense it depicts, and neither kind did. Across thirteen VLM judges, an aligned image changed 20.5% of labels and a misleading one 19.4%, close for every judge and both above the 11.6% produced by deleting the ignore-the-image instruction with the image left in place. Yet only 37% of the labels that differ between the two images moved toward the sense shown, and agreement with our human annotators is unchanged whether the image is absent, aligned or misleading. The effect is smaller in the seven judges that pass the alt-test than in the six that never do, but present in all of them: what moves a judge is that an image is there, not which of the two it is, so a substitutability verdict describes a configuration as much as a model.
Read the full abstract ▾
All authors Nagham Omar, Mahmoud Jabarin, Kinan Ibraheem, Lotem Peled-Cohen
Computation and Language
One Threshold Does Not Fit All Languages: Language-Conditional Deferral for Reliable and Efficient Low-Resource Text Classification
Bhanu Prakash Vangala and Vangala Navya
In the Global South, the lower-income countries of Africa, Asia, and Latin America where most of the world's
languages are spoken, a deployed text classifier usually runs on ordinary CPUs, serves many
languages with a single model, has few labeled examples in any of them, and relies on people to catch its mistakes. Such a system is only useful if it can promise how often it will be wrong: at most a fixed fraction of the labels it assigns on its own may be incorrect, and everything else must go to a person. Split conformal prediction delivers this promise through a single confidence threshold, normally estimated on validation data pooled across
languages. We ask whether the promise reaches every
language, and it does not. On MasakhaNEWS (16 African
languages) and AfriSenti (12
languages plus two never seen in training), a pooled threshold meets the 90% target on average but covers Somali at 77.5%, Tigrinya at 83.7%, and the two unseen
languages at 77.5% and 81.2%. Estimating one threshold per
language brings every
language to between 89.1% and 91.0% without retraining, and it shows how unequal the cost of the promise is: keeping it means sending 43% of Somali news and over 80% of Amharic and Xitsonga tweets to a person, against under 8% of Nigerian Pidgin news. One or two hundred labels per
language are enough and the models train in minutes on one CPU core, so the fix is affordable: calibrate, report, and budget human review one
language at a time.
Read the full abstract ▾
Machine Learning
Storage Is Not Strategy: State-Conditioned Support Control for LLM Unlearning
Tianhao Qian, Ziming Hong, Chongyang Gao et al. (+2 more)
Many localized large
language model (LLM) unlearning methods select a small parameter subset from a localization signal and keep it fixed during optimization. The parameters most associated with a target, however, need not be the best ones to update, and candidate interventions can change value as optimization proceeds. In a controlled experiment, a storage-localization score reaches an area under the receiver operating characteristic curve (AUROC) of 0.981, yet storage identity agrees with the better intervention on only 17/36 targets, while low-rank adaptation (LoRA) wins 35/36. We introduce Intervention Score, which ranks editable groups by the predicted effect of the actual unlearning update while accounting for collateral damage, and use it to form the static intervention-value baseline (Static-IV). We then introduce selective dynamic intervention re-ranking (DIR-R), which revisits that subset only when a calibrated probe justifies the comparison. On the Natural-TOFU
dataset, our method has positive descriptive margins in 19/20 comparisons between methods and objectives, although several are near zero. On the LACUNA localization-precision
benchmark, our mean terminal utility is higher in all six negative preference optimization (NPO) and SimNPO comparisons: NPO margins range from +0.431 to +0.848, and SimNPO margins range from +0.503 to +0.571. The gradient-difference (GradDiff) objective reveals substantial field dependence. Relative to Static-IV, the primary four-field GradDiff evaluation has six wins, six ties, and no losses, with mean and median paired gains of +0.165 and +0.0025. The evidence supports separating localization, initial intervention selection, and checkpoint-dependent support revision.
Read the full abstract ▾
All authors Tianhao Qian, Ziming Hong, Chongyang Gao, Kezhen Chen, Lixu Wang
Artificial Intelligence
Active Budget Can Kill Sensitivity: Diagnosing and Repairing TopK Sparse Autoencoder Reliability
Zhenting Huang, Bo Jiang, Junnan Liu et al. (+2 more)
Sparse autoencoders (SAEs) are increasingly scaled to wider dictionaries to recover fine-grained structure from large
language model activations. However, a feature is useful for interpretation only if it remains a stable unit of analysis when the same meaning is expressed in different surface forms. We study this reliability question for TopK SAEs via feature sensitivity. Experiments demonstrate that scaling selectively reduces the sensitivity of rare features, while common features remain comparatively stable. A controlled width\(\times k\) factorial experiment identifies the active budget k as the root cause: the degradation arises from the selection boundary rather than dictionary width alone. We attribute this failure to the geometry of TopK selection. The active margin, the distance to the cutoff, predicts feature loss without thresholds. Guided by this margin diagnosis, we introduce pairwise rank stabilization. Our method targets ordering failures at the cutoff and improves rare-feature sensitivity by \(8.83\) percentage points, while keeping reconstruction and alive-feature coverage near the baseline. Overall, our results suggest that wide TopK SAEs should be evaluated not only by reconstruction, sparsity, and feature count, but also by feature reliability under semantic variation and boundary geometry for stable interpretability.
Read the full abstract ▾
All authors Zhenting Huang, Bo Jiang, Junnan Liu, Zhixing Tan, Qianren Mao
Computer Vision
HandAnthro: Automated Hand Anthropometry from a Single Image
Fan Zhou, Shuairan Chen, Mengying Zhang et al. (+6 more)
Hand anthropometry supports protective-glove design, but existing measurement methods often require trained operators, specialized hardware, or manual landmarking. We present HandAnthro, which estimates 44 projected hand dimensions from a smartphone photograph of a palm-up hand on US letter-size paper. The pipeline reconstructs wrist-occluded paper boundaries for rectification, whitens non-hand pixels, and refines 41 anthropometry-specific landmarks from a fine-tuned You Only Look Once (YOLO) pose model using image-specific geometry and contours. Controlled evaluation comprised 720 captures from 45 held-out participants, each contributing 16 images across two smartphones, two backgrounds, two angles, and two nominal illumination settings. HandAnthro produced complete outputs for 704 captures (97.8%); among these, mean absolute error (MAE) was 3.80 mm per dimension against two trained operators' caliper measurements. Regional MAEs were 2.48 mm for non-thumb fingers, 6.04 mm for thumbs, and 6.17 mm for palm and wrist. In a researcher-assisted mobile-app pilot, automated batch processing returned all 44 dimensions for 260 of 268 retained, researcher-screened firefighter images (97.0%). A descriptive, unpaired comparison with an independent national firefighter reference yielded a mean absolute difference of 2.40 mm across 28 sex-by-dimension group-mean contrasts. These results characterize controlled measurement performance and researcher-assisted field feasibility for future distributed hand-anthropometry studies.
Read the full abstract ▾
All authors Fan Zhou, Shuairan Chen, Mengying Zhang, Yulin Wu, Sadegh Jafari, Sixing Yu, Rui Li, Ali Jannesari, Guowen Song
Computation and Language
AnthroDial: Benchmarking LLM Anthropomorphism in Autonomous Social Interaction
Wentao Liu, Xi Chen, Siyu Song et al. (+13 more)
Large
language models (LLMs) are increasingly deployed as social
agents, yet credible human-like interaction requires more than fluent responses or persona consistency.
Agents must autonomously decide whether, when, and how to communicate while adapting to evolving contexts, goals, and relationships. Existing research, however, lacks a unified approach to enabling, evaluating, and improving such capabilities in continuous, open-ended interaction. We introduce AnthroDial, a unified framework for developing anthropomorphic social
agents from three complementary aspects: MindFlow, a lightweight interaction harness that enables autonomous, asynchronous, and adaptive communication through a dynamic Mind Buffer; CAPS-Eval, a theory-grounded framework for evaluating cognitive, affective, and behavioral dimensions of anthropomorphic interaction; and a scalable training paradigm that combines SEEDS for environment expansion with DiAPO for adaptive capability optimization. We further construct evaluation
datasets covering everyday communication, game interaction, and long-horizon character interaction. Extensive experiments across diverse models and scenarios demonstrate improved interaction autonomy and naturalness, validate the reliability, discriminativeness, and agreement with human rankings of CAPS-Eval, and confirm the effectiveness of our training paradigm. Together, these components provide a unified framework for developing credible human-like social
agents in open-ended interaction.
Read the full abstract ▾
All authors Wentao Liu, Xi Chen, Siyu Song, Biao Yuan, Yu Zhang, Zhou Zhuotong, Jingying Zhou, Guohao Feng, Shasha Hu, Tianfu Wang, Shangshang Yang, Haoyang Liu, Youjia Li, Xiaokun Wang, Min Ji, Ji Wang
Machine Learning
Delta-Matching: Closing the Final Gap of Native 8-bit Training for LLMs
Haozhan Tang, Hao Kang, Han Cai et al. (+2 more)
Reliable FP8
attention remains a barrier to fully native 8-bit large
language model training. We derive how forward-backward inconsistencies produce stale delta and empirically show how it distorts training dynamics. Our stale-delta hybrid runs show a modest loss gap at 569M parameters but substantial loss increases and downstream degradation at 1.67B and 5.29B. QK normalization, NoPE (no positional encoding), and lower-learning-rate context extension mitigate or delay degradation without eliminating it. This pattern suggests accumulated optimization error that smaller models and short runs can conceal. We propose Delta-Matching, proving that it restores the softmax gradient's zero-row-sum invariant under the stated numerical assumptions. It enables native block-scaled FP8 in every forward and backward
attention-core matmul without architectural changes, smaller global batches, or auxiliary forward outputs. Across tested architectures, scales, and training stages, Delta-Matching matches BF16/FP32 mixed-precision training loss and overall downstream performance. We will release our implementation, trained models, and data recipes (https://jet-ai-projects.github.io/delta-matching).
Read the full abstract ▾
All authors Haozhan Tang, Hao Kang, Han Cai, Song Han, Chenyan Xiong
Computer Vision
FlowMap-OPD: Rollout–Kernel Separation for On-Policy Distillation of Few-Step Flow-Map Generators
Zhiqi Li and Bo Zhu
Few-step flow-map generators, including MeanFlow and consistency models, enable efficient sampling through long-range transport, yet their on-policy
distillation remains underexplored. We introduce FlowMap-OPD, an on-policy
distillation framework that separates student-state acquisition from teacher–student distribution comparison. A formulation based on state marginals establishes this separation, while flow–velocity consistency connects local supervision to the deployed long-range map. Within this framework, we develop flow-map, induced-velocity, and instantaneous-velocity distribution supervision, each paired with a separately specified native flow-map rollout. Cross-capacity ImageNet experiments across three teacher rewards identify instantaneous-velocity distribution supervision with independently tunable student consistency as the most effective choice. In text-to-image experiments, FlowMap-OPD demonstrates strong multi-specialist consolidation capabilities and surpasses multi-reward Flow-Map GRPO in task performance and convergence speed.
Read the full abstract ▾
Computer Vision
RelayVSR: Large-Small Model Collaboration for Efficient Real-World Video Super-Resolution
Xijun Wang, Xin Li, Zirui Lang et al. (+3 more)
Large generative models can recover realistic detail in real-world
video super-resolution (VSR), but processing an entire
video with them is computationally expensive. In this work, we present RelayVSR, a streaming VSR framework built on the Sparse Generative Relay mechanism. A large generative model generates reference latents for sparse keyframes, while a lightweight VSR network uses these references and low-resolution
video to super-resolve every frame. The lightweight VSR network, implemented as a Dual-
Memory Video Transformer, reuses keyframe information across frames and updates recent
video context, supporting first-keyframe conditioning and dual-endpoint conditioning with bounded lookahead. However, errors in shared keyframes can propagate and accumulate across output frames, making keyframe quality alone an insufficient optimization target. We address this collaboration gap with
Video-Aware Reference Optimization (VARO), which uses reinforcement learning to update the large generative model with two reward levels: a system-level reward evaluates
videos produced by the fixed lightweight VSR network, while a reference-level reward evaluates decoded keyframe quality. VARO improves final
video quality over direct joint training, and its dual-level rewards outperform a system-level reward alone. At 1080p on a single NVIDIA A100 80GB, dual-endpoint RelayVSR with a 15-frame keyframe interval reaches 29.29 FPS, 13.82 GB peak GPU
memory, and 0.327 s first-frame model latency, compared with 7.80 FPS, 24.447 GB, and 2.83 s for FlashVSR-Tiny. The code is available at https://github.com/kopperx/RelayVSR.
Read the full abstract ▾
All authors Xijun Wang, Xin Li, Zirui Lang, Suhang Yao, Haoran Li, Zhibo Chen
Software Engineering
Is manual software optimization a thing of the past?
Pavlin G. Poličar, Martin Špendl and Tomaž Hočevar
Scientific software is increasingly required to process larger
datasets while maintaining acceptable execution times. Software optimization traditionally requires substantial expertise in programming,
algorithms, and numerical methods. Recent advances in large
language models (LLMs) offer the possibility of automating much of this process. We investigate whether LLM-based
agents can autonomously achieve substantial performance improvements in scientific software, including mature implementations that have already been extensively optimized by human developers. We tasked an LLM-based
agent with optimizing software for three computational problems: t-SNE, single-sample gene set enrichment analysis (ssGSEA), and graphlet counting. Humans defined the scope, correctness criteria, and a verification mechanism, after which the
agent worked autonomously, in some cases for several hours. Code maintainers reviewed each resulting implementation and verified its correctness. The optimized implementations were faster in all tested configurations, by up to two orders of magnitude over the fastest existing tools. The improvements included low-level code optimizations, mathematical reformulations, and an entirely new
algorithm for graphlet counting. Software optimization can increasingly be delegated to autonomous
agents, with the human role shifting from implementing optimizations to deciding which software to optimize, defining objectives, providing verification mechanisms, and ensuring the correctness of the final software. For well-scoped, verifiable problems, we argue that manual software optimization may be a thing of the past.
Read the full abstract ▾
Computer Vision
Evaluation Choices Shape Biomedical ML Claims: A Pediatric Pneumonia Benchmark Case Study
Bhanu Prakash Vangala, Sowmya Guda, Latha Peddi et al. (+1 more)
Biomedical machine learning papers often compress model performance into one headline number. That number can look like a property of the model even when it depends strongly on how the
benchmark was evaluated. We study this problem on the widely used Kermany pediatric chest radiograph
dataset using nine image classifiers and a controlled evaluation protocol. Under the same protocol, the eight pretrained backbones differ by only 0.026 AUROC. In contrast, changing whether the backbone is frozen or fine-tuned changes AUROC by 0.044 on average, and changing the decision threshold changes balanced accuracy by 0.090 on average. The official test split is also measurably different from the training pool: a partition classifier distinguishes them at AUC 0.697, rising to 0.898 for normal radiographs. Most strikingly, a classifier using only file properties, with no image anatomy, reaches 0.992 balanced accuracy within the training pool but falls to 0.496 on the official test split. Validation-fitted thresholds and calibration also transfer imperfectly. These results show that a high
benchmark score can support different conclusions when the split, training policy, threshold, metric, calibration, and uncertainty are not communicated with it. We end with a seven-item reporting recommendation in which each item is tied to an effect measured in the study
Read the full abstract ▾
All authors Bhanu Prakash Vangala, Sowmya Guda, Latha Peddi, Navya Vangala
Numerical Analysis
Running error bounds in finite element kernels
Michal Habera, Paul T. Kühner, Matteo Croci et al. (+1 more)
Rounding errors in finite element computations can lead to a complete loss of accuracy, stalled convergence, and incorrect results. Moreover, the effects of rounding errors accumulated within automatically generated and compiled kernels are difficult to analyze a priori. We present the first software framework for automated rounding error estimation within finite element kernels. The proposed methodology is based on an a posteriori technique called Running Error Analysis (REA), where a forward error estimate is automatically computed concurrently with the value. An open-source implementation is provided for the FEniCS Form Compiler (FFCx), based on a C++ backend for generating type-generic templated kernels over a custom arithmetic type that tracks both the value and its error estimate. We demonstrate REA on two examples. First, we use it to detect catastrophic cancellation in the assembly of a Neo-Hooke hyperelastic model in the small deformation regime. A series expansion circumvents the cancellation problem and the computed error estimates show this. Second, we study the assembly of the Laplace operator on a near-degenerate mesh. We demonstrate that our REA implementation typically incurs only 2-4x performance overhead. Applications of this work include robust reduced-precision computations in embedded systems, numerical debugging of new, possibly ill-conditioned or unstable PDE formulations, and guiding the design of mixed-precision kernels.
Read the full abstract ▾
All authors Michal Habera, Paul T. Kühner, Matteo Croci, Andreas Zilian
Machine Learning
Scaling Influence Functions in LLMs through Eigenbasis-Corrected One-Bit Gradient Projection
Jaeseung Heo, J Rosser and Dongwoo Kim
Influence functions estimate how individual training examples affect the behavior of large
language models (LLMs). Analyzing how training data influence different behaviors of an LLM involves repeated influence computation. Reusing stored training gradients reduces the computational cost, but storing full gradients is prohibitively expensive at LLM scale. We study how to compress these gradients while preserving influence estimates for future queries that are unknown at storage time. Through a worst-case analysis, we characterize the optimal fixed-dimensional linear representation and propose eigenbasis-corrected one-bit gradient projection (EOGP) to approximate it at scale. Specifically, EOGP uses EK-FAC to reduce gradient dimensionality, then applies PCA within the retained subspace to learn compression directions from the training gradients. We then apply one-bit quantization to the resulting coordinates, allowing more coordinates to be retained within a fixed storage budget. On GPT-2, EOGP predicts retraining outcomes more accurately than the evaluated compression baselines while using one-sixteenth of their per-example storage. On OLMo 2 SFT models from 1B to 32B parameters, EOGP remains competitive with the baselines allocated over 100 times as much storage per example.
Read the full abstract ▾
Machine Learning
Counterfactual Probing for Parallel Unmasking with Hidden Forest Structure
Ryotaro Kawata, Satoshi Hayakawa and Taiji Suzuki
Masked generative models offer parallel
token prediction, but accurate parallel sampling must account for dependencies among
tokens. When dependencies are unknown, finding safe batches also costs model evaluations. We study whether total evaluations, including discovery, can be sublinear in sequence length $N$; sublinear sequential depth then follows. We consider discrete distributions with hidden forest structure, accessed through a fixed approximate conditional oracle. Under explicit regularity conditions and uniform Hellinger error bounds, for any fixed target accuracy $\varepsilon\in(0,1/8]$ and sufficiently large $N$, our sampler achieves seed-averaged total-variation error at most $\varepsilon$, with total masked-state submissions and sequential depth both bounded by $\widetilde{O}(N^C \varepsilon^{-a})$ for constants $0<C<1$ and $a>0$. These guarantees use
polynomial vocabulary size and an edge-response lower bound set by $N$ and $\varepsilon$. The sampler shares evaluations of hypothetical reveals across dependence tests to identify safe parallel batches without requiring full recovery of the hidden forest. A tunable parameter trades probing cost against irreversible commit rounds. In the same class, any admissible irreversible product-commit sampler attaining the same seed-averaged accuracy requires $\Omega(N^c \varepsilon^b)$ counterfactual submissions or commit rounds in the worst case, for constants $c,b>0$.
Read the full abstract ▾
Systems and Control · Cross-listed from math.OC
Practical Stabilization of Switched Affine Systems under Dwell Time: From Polytopic to p-Norm Lyapunov Functions
Felipe Cinto, Alexis J. Vallarella, Hernan Haimovich et al. (+1 more)
This paper addresses the stabilization of switched affine systems under dwell-time constraints around a desired operating point that is not a common
equilibrium of the subsystems. Since asymptotic stabilization is generally unattainable in this setting, the objective is to ensure that trajectories converge to and remain within a prescribed region containing the desired operating point. The main contribution is the development of Lyapunov-based tools that accommodate target regions more general than those induced by quadratic Lyapunov functions. In particular, we establish a constructive Lyapunov characterization for a broad family of weighted $p$-norm functions, which generalizes the classical quadratic Lyapunov equivalence and underpins the proposed hybrid-control and dwell-time developments. Focusing on the case in which the desired region is a polytope, and building on existing Lyapunov-based methods, we develop a constructive two-step method that starts from a polytopic Lyapunov certificate for the average system and yields a smooth weighted $p$-norm Lyapunov function for all sufficiently large $p$. We prove that this extension guarantees practical asymptotic stability of the desired operating point and yields a Lyapunov-certified invariant region under minimum dwell-time switching. Numerical examples illustrate the effectiveness of the proposed method.
Read the full abstract ▾
All authors Felipe Cinto, Alexis J. Vallarella, Hernan Haimovich, Paulo C. Pellanda
Computation and Language
Can Vision-Language Models Stay Helpful When Facing Implicit Risks? Intent-Privilege OPSD for Efficient Safety-Helpfulness Alignment
Haotian Deng, Wenbin Xing, Gang Xu et al. (+5 more)
Vision-
Language Models (VLMs) remain vulnerable to cross-modal implicit risks: visual and textual inputs that appear benign in isolation can jointly elicit unsafe responses. Existing safety methods often require large preference
datasets, costly multi-rollout training, or additional safeguards at inference time. They may also sacrifice helpfulness by directly refusing requests that could be answered safely. In this paper, we propose Intent-Privilege On-Policy Self-
Distillation (OPSD), which leverages evidence-grounded intent as privileged supervision during training to help VLMs recognize implicit risks and provide safe, useful responses instead of blanket refusals. OPSD distills a teacher's intent-conditioned preferences over responses into a student using a single rollout per
prompt; the student then responds without intent annotations or an additional safety module. With only 1,447 safety-specific examples - 95% fewer than standard preference
datasets - OPSD reduces training time by 5x relative to multi-rollout GRPO-style training and average inference length by 7%. It attains the highest ratio for joint safety-helpfulness success, which measures the proportion of responses that are both safe and helpful, across all five evaluation groups. Remarkably, on pooled SIUO+HoliSafe, this success ratio rises from 43.9% to 53.5%. These results show that training-time intent supervision can improve both safety and helpfulness while substantially reducing data, training, and inference costs.
Read the full abstract ▾
All authors Haotian Deng, Wenbin Xing, Gang Xu, Tao He, Jinkai Zheng, Chun Li, Zheng Zhu, Ming Li
Machine Learning
Behavioral Convergence Without Representational Convergence: Persistent Training-History Dependence in Neural Networks
Ertuğrul Mutlu
Neural networks trained toward the same final objective can reach similar predictive performance while retaining internal representations shaped by earlier training history. We study this effect using controlled sequential-training experiments in which paired convolutional networks start from identical weights, experience reversed task orders, and then receive the same deterministic common-relaxation distribution. Across 20 paired MNIST runs, 16 satisfy a predeclared behavioral-matching criterion, yet their matched representations retain a mean history score of 0.139 (95% bootstrap CI: 0.127-0.153) and approximately 3.1% prediction disagreement. Extending common relaxation to 50,000 optimizer updates does not erase the measured difference: across five paired seeds, the representation-history score remains 0.190 (95% bootstrap CI: 0.161-0.219) at the end of the measured horizon while the mean accuracy gap is only 0.18 percentage points. Fresh linear probes show that, with sufficient labeled data, the two histories retain practically equivalent linearly accessible class information. A same-label rotated-MNIST control reproduces the effect: all five paired seeds reach behavioral matching while retaining a mean representation-history score of 0.162. Finally, a matched-learning-rate ReLU-LeakyReLU control reduces the 50,000-update representation residue by 0.040 on average in all five paired seeds, providing directional evidence that activation-mediated plasticity contributes to the persistence of training-history effects. These results provide protocol-scoped evidence that behavioral convergence need not imply representational convergence and that optimization history can leave measurable internal traces after prolonged common training.
Read the full abstract ▾
Artificial Intelligence
Mixture of Self-Improving Branches For Agent Harness Optimization
Haoyu Dong, Yuhang Zhou, Zihao Lin et al. (+6 more)
Harness optimization provides a practical setting for recursive self-improvement (RSI), where
agent-generated modifications inform subsequent changes through execution feedback. Recent work such as Meta-Harness implements this process through iterative code generation and evaluation, but retains a fixed development set and proposal policy. These constraints channel
evolution along a single search trajectory, increasing the risk of converging to a local optimum. We make the improvement process itself adaptive by organizing search into branches with evolving development subsets and proposal policies. Each branch retains development cases solved by more of its leading harnesses than by those of other branches, drops cases solved by every leading harness across all branches, and revises its proposal policy using its own search history. To deploy the resulting complementary harnesses, we propose a router to select one development-selected branch head for each new input before execution. Across mathematical
reasoning and agentic coding
benchmarks, our system achieves relative improvements over Meta-Harness of 34.8% on Olympiad-level mathematical
reasoning, 11.6% on Terminal-Bench 2.0, and 3.8% on SWE-bench Lite, with harness selection and router configuration based solely on development data. These results show that evolving branch objectives and proposal policies can yield complementary harnesses whose strengths a router combines without access to test outcomes.
Read the full abstract ▾
All authors Haoyu Dong, Yuhang Zhou, Zihao Lin, Yifan Wu, Bo Peng, Mingyi Wang, Xiangjun Fan, Lizhu Zhang, Zhuokai Zhao
Artificial Intelligence
Can a Cacheable Decision Model Follow Rules?
Dushyant Rajput, Nirdesh Chauhan and Siddharth Kosaraju
Certo is a small non-generative decision model (Qwen3-4B): it scores candidate actions from their text and returns a probability, instead of generating an answer. The accurate design reads the state, the rules, and each candidate together (a joint scorer), so cost grows with the menu. Independent encoding lets each candidate be encoded once and reused across states (about 5x cheaper at 77 candidates), but separates state from candidate. We ask how much rule-sensitivity survives that move, and whether it can be trained back. Four experiments on Certo: (1) the tested conversion to cacheable scoring loses rule-sensitivity (recall@1 1.00 -> 0.24) while the joint scorer holds 1.00, and a shortlist+rerank rescue fails; (2) targeted counterfactual supervision restores strong performance on held-out synthetic rule tasks (paraphrase, counterfactual, composition; reproducible across seeds), though we do not isolate whether predictions depend on the supplied rule; (3) on real rules the added benefit is not established – after fixing a truncation confound, the joint scorer wins significantly on the short tier (0.861 vs 0.500) and directionally on the hard tier (0.655 vs 0.483, n=29); (4) a matched cross-domain real-prose mixture did not help and reduced contract accuracy (-9.3, -16.2 points). A cacheable encoder can be made rule-sensitive on its training distribution, but transfer to unseen-source real rules is not established; the joint scorer keeps an edge at the cost of caching.
Read the full abstract ▾