Computation and Language
DiffIE: Diffusion-based Open Information Extraction
Konstantin Fedorov and Valentin Malykh
A single sentence often expresses multiple valid relational triplets, which makes Open Information Extraction (OpenIE) fundamentally a multi-output task. Existing neural systems handle this by autoregressive generation, which is flexible but slow and prone to redundancy, or by fixed-slot prediction, which is efficient but couples the extraction budget to training. We introduce DIFFIE which instead treats the stochasticity of conditional discrete
diffusion as the extraction mechanism itself: independent reverse-
diffusion trajectories over per-
token role tags produce a pool of candidate triplets, which are clustered under lenient matching and ranked to form the output. Both the pool size and the number of returned extractions are inference-time choices, decoupling the extraction budget from training and exposing test-time compute as a tunable axis. DIFFIE achieves the new state of the art in CaRB (1-1) both F1 and AUC, and outperforms the strongest rule-based system (ClausIE) in BenchIE; it also remains competitive in standard CaRB and WiRe57 evaluations, giving the best average score among systems that report all four
benchmarks. Ablations show that uniform discrete
diffusion outperforms absorbing state
diffusion in our setting, and that a matched non-
diffusion stochastic tagger does not reproduce its gains. Our results indicate that
diffusion stochasticity is an effective mechanism for structured prediction tasks with multiple valid outputs.
Read the full abstract ▾
Computation and Language
Efficient GUI Agents: A Systems Survey of Observation, Memory, Action, and Runtime Optimization
Bizhe Bai, Jiakang Yuan, Hongming Wu et al. (+8 more)
GUI
agents increasingly operate across websites, mobile apps, and desktop environments, yet the field still reports progress primarily through task success. We argue that practical deployment depends equally on efficiency: how much context, computation, action budget, and runtime overhead an
agent consumes while succeeding. This survey studies efficient GUI
agents through an end-to-end systems lens that preserves the current technical axes of observation efficiency, context and
memory efficiency, action efficiency, and planner-side/system efficiency. For each subsection, we expand the seed literature through targeted search plus backward and forward citation chaining, then synthesize the dominant mechanisms, reported efficiency signals, and new overheads they introduce. Across the literature, recent progress converges on a small set of recurring ideas: selective reading instead of full-context ingestion, global-to-local visual allocation, recoverable
memory rather than raw history replay, verification-aware control, and hybrid runtimes that can switch between GUI and non-GUI execution. We conclude by identifying the main open problems, including honest accounting of verifier cost, cross-
benchmark comparability, and co-design of observation,
memory, and execution layers under real latency and
privacy constraints.
Read the full abstract ▾
All authors Bizhe Bai, Jiakang Yuan, Hongming Wu, Xinyue Wang, Jie Ren, Siyao Chen, Yuchen Ya, Fan Bai, Pai Peng, Huafeng Qin, Tao Chen
Robotics
Contact-Constrained Lower-Limb Joint-Offset Calibration for Humanoid Robots
Kaixiang Lu, Haiyu Lan, Chunxiao Qiao et al. (+5 more)
Accurate joint encoder offsets are essential for kinematic consistency in
humanoid lower limbs, yet existing calibration methods typically require external motion-capture systems or fiducial targets. We present a self-contained calibration framework exploiting only onboard joint encoders and a pelvis-mounted IMU during static double-support contact. The inter-foot transform from forward kinematics must stay constant when both feet are fixed; minimizing its posture-dependent dispersion yields a nonlinear least-squares problem over the 12-dimensional offset vector. A Hessian eigenstructure analysis shows that parallel pitch axes induce a rotational coupling. Orientation residuals then observe only the pitch-offset sum, while translation and posture diversity set the remaining numerical observability. For the A3 pitch-to-roll-to-yaw ordering, hip-roll and hip-yaw excitation reduce hip-pitch coupling. A standing-posture knee prior then anchors the remaining weak pitch-chain decomposition. Simulation and real-machine injection tests show consistent recovery, and on held-out recordings calibration reduces foot-height RMS residuals from 4.26 to 2.20 mm on A3 and from 8.03 to 1.43 mm on A2. An independent
LiDAR-inertial reference checks the pitch-coupled channel. Removing an injected pitch offset moves the leg-odometry vertical drift back toward the
LiDAR trajectory. A few static double-support stances thus provide contact-consistent corrections for well-excited directions. Individual offsets in the weak pitch chain remain prior-dependent.
Read the full abstract ▾
All authors Kaixiang Lu, Haiyu Lan, Chunxiao Qiao, You Li, Chengyuan Luo, Enyu Li, Peiwen Lin, Chuang Wang
Machine Learning
Bayes-Optimal BER and AUC: Estimation and Evaluation of Estimators
Ryota Ushio, Takashi Ishida and Masashi Sugiyama
A fundamental quantity in machine learning is the optimal performance achievable by any model on a given task. Estimating this quantity allows us to distinguish the irreducible part of the error from a deficiency of the model, telling us how much room for improvement remains. Recent work has shown that the Bayes error, or equivalently the optimal accuracy, can be estimated from soft labels in binary classification. However, accuracy is often a poor summary of performance in settings with severe class imbalance or noisy annotations, where metrics such as the balanced error rate (BER) and the area under the ROC curve (AUC) are more appropriate. We address this gap with two complementary contributions. (i) Estimation. We propose soft-label-based
estimators for the optimal BER and AUC. We first consider the clean setting in which true soft labels and the class prior are known, and then extend the
estimators to a more realistic setting in which the class prior is unknown and the observed soft labels are corrupted by an unknown order-preserving transformation, possibly followed by additive noise. In the latter setting, we approximately recover the clean soft labels via isotonic regression with auxiliary hard labels, estimate the class prior with a clipped mean of the hard labels, and derive finite-sample error bounds for the resulting plug-in
estimators. (ii) Evaluation. Since the optimum is unobservable on real
datasets, evaluating any such
estimator is itself nontrivial. We extend the FeeBee framework, originally proposed for evaluating Bayes-error
estimators, to the optimal BER and AUC. The resulting procedure provides practical evaluation scores without requiring knowledge of the optimum, and applies to any
estimator of the optimal BER or AUC, not only our proposed ones. Experiments on synthetic and real-world
datasets validate both the
estimators and the evaluation procedure.
Read the full abstract ▾
Information Retrieval
Genuine Information Needs of Social Scientists Looking for Data
Andrea Papenmeier, Thomas Krämer, Tanja Friedrich et al. (+2 more)
Publishing research data is widely expected to increase its reuse and to inspire new research. In the social sciences, data from surveys, interviews, polls, and statistics are primary resources for research. There is a long tradition to collect and offer research data in data archives and online repositories. Researchers use these systems to identify data relevant to their research. However, especially in data search, users' complex information needs seem to collide with the capabilities of data search systems. The search capabilities, in turn, depend to a high degree upon the metadata schemes used to describe the data. In this research, we conducted an online survey with 72 social science researchers who expressed their individual information needs for research data like they would do when asking a colleague for help. We analyzed these information needs and attributed their different components to the categories: topic, metadata, and intention. We compared these categories and their content to existing metadata models of research data and the search and filter opportunities offered in existing data search systems. We found a mismatch between what users have as a requirement for their data and what is offered on metadata level and search system possibilities.
Read the full abstract ▾
All authors Andrea Papenmeier, Thomas Krämer, Tanja Friedrich, Daniel Hienert, Dagmar Kern
Artificial Intelligence
Improving Evaluation Realism with Inference-Time Compute and Deployment Scaffolds
Axel Ahlqvist, Richard Guan, Juan-Pablo Rivera et al. (+6 more)
A core obstacle to
alignment evaluation is evaluation awareness: capable models can tell when they are being tested rather than deployed, weakening the conclusions a safety evaluation can support. We present two techniques that make simulated
alignment evaluations harder to distinguish from real deployments. Our first technique, critique refinement, spends additional inference-time compute on each simulator action: the simulator generates multiple candidate actions, refines them using feedback from an instance of the target model on how to make them more realistic, and continues the evaluation with the most deployment-like candidate. Our second technique, DISH (Deployment-Imitating SWE-
Agent Harness), wraps the target in an
agent harness, reducing the gap between simulated and real deployment environments in coding settings. We test the techniques on multiple target models and find that applying both yields larger realism gains than either alone. We show that automated approaches can improve the realism of
alignment evaluations, and that they compare favorably to spending the extra compute on more audit attempts.
Read the full abstract ▾
All authors Axel Ahlqvist, Richard Guan, Juan-Pablo Rivera, Adeline Kassler, Dmitrii Troitskii, Alexandra Souly, Kai Fronsdal, Robert Kirk, John Hughes
Computer Vision
Domain shift-robust object detection with GenAI image editing
Isabel D. Stein, Thijs A. Eker, Sebastiaan P. Snel et al. (+4 more)
Object detectors often degrade under domain shifts such as changes in lighting, weather, or occlusion. These shifts alter object appearance and expose a reliance on visual shortcuts learned from the training distribution that do not generalize across domains. Acquiring sufficient real-world samples to capture such domain variation is particularly difficult in specialized, low-data settings. Recent advances in
diffusion-based generative image editing have shown promise for improving the in-domain performance of object detectors through synthetic data augmentation. However, their potential to improve out-of-domain robustness remains largely unexplored. We hypothesize that generative image editing can simulate a controlled domain shift in training data, effectively bridging the gap between source and target domains. To test this, we studied camouflaged military vehicle detection as a challenging domain shift scenario. Detectors trained on uncamouflaged data demonstrate substantial degradation on real test imagery containing foliage, netting, and multi-spectral camouflage across 15 vehicle classes in close-up, ground-level imagery. We used two
diffusion-based editing models, Qwen Image Edit 2509 and Flux.2 Dev, to synthetically add camouflage to the training data, alongside a LoRA fine-tuned version of Qwen. A non-generative black-bar occlusion baseline served as a lower bound on augmentation quality. Using a GroundingDINO detector trained on real and synthetic data, generative camouflage augmentation yielded substantial mAP improvements for foliage (+20.1) and netting (+14.4) camouflage. Generating multi-spectral camouflage proved more challenging, but LoRA fine-tuning improved performance by 4.4 mAP over the uncamouflaged baseline.
Read the full abstract ▾
All authors Isabel D. Stein, Thijs A. Eker, Sebastiaan P. Snel, Ella P. Fokkinga, Klamer Schutte, Luca Ambrogioni, Friso G. Heslinga
Computers and Society
Meeting the Coming Wave: The Emerging Politics of AI and Work across 33 Parliaments
Juliana Chueri and Petter Törnberg
A new politics of artificial intelligence and work is taking shape across party systems, but comparative politics has yet to map it. Using 1,514,950 parliamentary
speeches from 33 parliaments (2023-2026), we show this politics follows a different logic than political economy expects. Research anticipates that technological disruption generates demands for compensation; instead, compensation accounts for just 2.3% of response-frame mentions, while enablement and investment dominate (55.2%), regulation and restriction follow (21.8%), and training (20.6%) appears at similar rates across families. Parties disagree instead over what AI means for work and how far this technology should be restrained. The mainstream and radical right support unrestricted enablement; the left is critical but divided on remedy. Social democrats stay adoption-oriented; greens split evenly. The radical left is the clearest force for restriction. The AI conflict thus concerns not compensation after disruption, but whether politics should enable technological change or govern its trajectory.
Read the full abstract ▾
Machine Learning
SEAL: Reinforcing Global Safety in Mixture-of-Experts through Shared Expert ALignment
Qingyu Meng, Yiwei Zha, Jiahuan Pei et al. (+3 more)
Mixture-of-Experts (MoE) is a scaling architecture for large
language models that activates only a small subset of expert modules per
token, enabling massive parameter growth with nearly constant computation. Recent Hybrid MoE architecture adds shared experts to capture consistently useful representations, further improving stability and generalization. MoE now powers many flagship open-source and commercial models, yet remains vulnerable to
adversarial attacks. Specifically, sparse routing introduces a structural vulnerability: MoE safety hinges on which experts are activated, and adversaries can subvert this selection through jailbreak
prompts, malicious fine-tuning, and weight-level
pruning of safety-critical
neurons. Existing defenses primarily focus on hardening the router, but an adversary may still manipulate or bypass the routing trajectory due to the routing process's nondeterministic nature, thereby collapsing the defense. To cope with this problem, we first identify theoretically and empirically that shared expert, an always-activated component containing a small proportion of safety-critical
neurons, can overcome the uncertainty of sparsely activated routing path and serve as a router-independent anchor to enhance global safety
alignment. Based on this insight, we propose SEAL, a training-time parameter-efficient defense that produces a plug-and-play adapter attached to shared expert, and SEAL++, a variant that adds an orthogonal constraint preserving pre-existing safety subspaces during training. We evaluate SEAL and SEAL++ across six attack scenarios that combine three
adversarial inputs (harmful prompting, jailbreak, malicious fine-tuning) with and without
neuron pruning. SEAL reduces attack success rate (ASR) by up to 60%, at a capability cost of at most 1.4% on a five-
benchmark average. Additionally, SEAL can seamlessly integrate with router-level ......
Read the full abstract ▾
All authors Qingyu Meng, Yiwei Zha, Jiahuan Pei, Koen Hindriks, Herbert Bos, Min Chen
Artificial Intelligence
SCX Router: Streaming Zero-Shot Model Selection with a Decoder-KV Classifier and a Real-World Task Ontology
Ihor Stepanov, Aleksandr Smechov, Mykhailo Shtopko et al. (+2 more)
The rapid proliferation of large
language models (LLMs) and the growing diversity of their applications presents a unique optimization opportunity: selecting the right model for the task, while optimizing for speed, cost, and quality at a per-task level. However, inference endpoints can vary widely in quality, price, latency, context support, tool use, domain expertise, and
reasoning behavior. This heterogeneity makes manual heuristics difficult to maintain and unlikely to achieve consistently favorable speed–cost–quality trade-offs on their own. We introduce \router{}, a lightweight GLiClass-based router that assigns a suitability score to each inference-time model label without autoregressive generation. The released 0.6B-parameter checkpoint combines a Qwen3 decoder with a shallow bidirectional scorer. Its decoder-KV execution path preserves a text-only key–value cache across a session, encodes only new dialogue turns, and evaluates transient candidate-label
tokens without adding them to the persistent cache. The same checkpoint also predicts task type, difficulty,
reasoning mode, and expected output length, and supports custom zero-shot labels. For task generation, we construct a task ontology with 23 families, 115 task types, 345 routable subtypes, 1,173 synthetic examples, and an orthogonal axis of 30 domains. Using this structure, we generate 150,000 verifier-scored tasks and 15,000 open-ended tasks. We then train the Qwen3 decoder on these tasks, while explicitly separating learned request prediction from per-task policies for attributes such as eligibility, cost, cache reuse, safety, and sovereignty. Across six LiveBench subsets, the router outperforms the mean candidate; on the selected 1,000-task subset, it achieves an aggregate top-1 score of 0.707 versus 0.696 for the strongest fixed model, with
benchmark-dependent gains.
Read the full abstract ▾
All authors Ihor Stepanov, Aleksandr Smechov, Mykhailo Shtopko, Dmytro Vodianytskyi, Oleksandr Lukashov
Computer Vision
VoRTeC: Taming Foundation Flow for One-step Real time Video Compression
Yichong Xia, Qinhong Wu, Bin Chen et al. (+3 more)
Ultra-low bitrate
video compression still faces critical challenges: traditional neural
video compression inevitably introduces blurring artifacts, while
diffusion-based generative
video compression suffers from excessive decoding latency and poor temporal consistency. To address these issues, we propose $\mathtt{VoRTeC}$, a
Video Compression framework built upon a foundational flow model (Wan2.1). By compactly encoding latent
video representations, predicting the positions of compressed representations along flow trajectories, and integrating multi-scale priors, $\mathtt{VoRTeC}$ enables the compressor to harness generative
video flow priors effectively. Without accessing the parameters or gradients of flow matching networks, our framework achieves one-step decoding and reconstructions with high perceptual fidelity. Meanwhile, we maintain consistency across frame groups via tail-frame reuse and prior caching. Extensive experiments demonstrate that our method reduces bit consumption by 58% compared to prior
diffusion-based approaches, with decoding speed boosted by 3 to 197 times: $\mathtt{VoRTeC}$ achieves a decoding speed of 13 FPS at 720p and 32 FPS at 480p.
Read the full abstract ▾
All authors Yichong Xia, Qinhong Wu, Bin Chen, Jinpeng Wang, Zeyuan Chen, Haoqian Wang
Information Theory
Agentic UE-CoMIMO for 6G Terminals: From Virtual Antenna Augmentation to AI-Native Virtualization
Chao-Kai Wen, Yen-Cheng Chan, Lung-Sheng Tsai et al. (+2 more)
End-user-centric collaborative
MIMO (UE-CoMIMO) lets nearby devices form a virtual multi-
antenna terminal to overcome the
antenna limitations of individual user equipment. Extending such cooperation to communication, sensing, computing, and task-relevant information exchange requires a control layer that can interpret user intent, select cooperation mechanisms, and replan as conditions change. This article introduces Agentic UE-CoMIMO, in which device micro-
agents, a smartphone or CPE hub
agent, and edge/network
agents coordinate device participation, relay modes, traffic splitting and duplication, compute placement, semantic-
token exchange, and
topology reconfiguration. Two system-level scenario studies on creator-centric live streaming and wearable-collaborative blind-spot sensing compare the proposed controller with capability-matched adaptive baselines. The results show that, by anticipating changes and preparing cooperation and fallback actions in advance, agentic control sustains high-quality streaming for longer and maintains blind-spot warnings through device outages. We also discuss the associated standardization, interoperability, trust, and validation challenges.
Read the full abstract ▾
All authors Chao-Kai Wen, Yen-Cheng Chan, Lung-Sheng Tsai, Pei-Kai Liao, Geoffrey Ye Li
Computer Vision
If It Moves, Radar Knows: A Physics-Aware Radar Transformer for Class-Agnostic Moving-Object Detection
Yinghao Sun, Shuguang Li, Jinliang Shao et al. (+1 more)
Detectors trained on closed-set annotations can miss rare moving objects outside the training taxonomy. Automotive radar provides category-independent Doppler motion cues and is less affected by adverse illumination and weather, but sparse, noisy returns hinder class-aware 3D box detection. Surface location and velocity remain useful for motion
reasoning and collision avoidance when full box geometry is difficult to recover. We present the Physics-Aware Radar
Transformer (PART), a fully sparse radar-only detector that predicts existence confidence, a representative surface point, and 2D ground-plane velocity for each moving-object hypothesis. Doppler-Aware Query Initialization (DAQI) replaces scene-independent learned queries with input-dependent proposals by clustering radar returns in position and velocity, easing query-object assignment in sparse scenes. Physics-Guided Cross-
Attention (PGCA) incorporates radial-Doppler consistency and radar cross section (RCS) into query-point association. Uncertainty-aware supervision randomly masks ground-truth objects and assigns soft existence targets to ambiguous radar-supported queries, reducing reliance on exhaustive annotations. With only 1.1 million parameters, PART achieves a class-agnostic average precision (CA-AP) of 0.8827, a mean average surface translation error (mASTE) of 0.3188 m, and a mean average velocity error (mAVE) of 0.8084 m/s on nuScenes. It attains 0.9203 recall on rare and safety-relevant categories excluded from the standard evaluation and remains effective at night, in rain, and under severe occlusion. Inspection of apparent false positives shows that some predictions correspond to moving objects absent from the nuScenes annotations. Code and pretrained model weights will be publicly available at https://github.com/sunyinghao-uestc/PART.
Read the full abstract ▾
All authors Yinghao Sun, Shuguang Li, Jinliang Shao, Tieshan Li
Computer Vision
Diffusion-Encoding Gaussian Field for Joint k-q dMRI Reconstruction
Zhibo Chen, Yajuan Huang, Yu Guan et al. (+3 more)
Diffusion MRI requires repeated k-space acquisitions over multiple
diffusion-encoding directions, making acquisition time dependent on both spatial and angular sampling. Existing joint k-q methods either associate directional parameters with fixed voxels or separate spatial reconstruction from angular completion. However,
diffusion-weighted images acquired under different directions share the same anatomical organization, while their local signal intensities vary with
diffusion encoding. Existing formulations do not fully exploit the complementarity between shared anatomy and direction-dependent signal variation. Consequently, residual spatial errors may be misinterpreted as genuine angular variation and propagated to unobserved directions. We propose a subject-specific spatial-angular Gaussian field for self-supervised joint k-q dMRI reconstruction. Shared 3D Gaussian primitives provide local spatial support, with each primitive carrying a continuous q-conditioned tensor-residual response. The signal at each location is synthesized from multiple overlapping primitive responses, coupling neighboring spatial regions and
diffusion directions. The field is progressively optimized from undersampled k-space measurements of observed directions, without fully sampled targets or held-out-direction supervision. Experiments on three HCP
diffusion shells under multiple acceleration settings demonstrated consistent improvements in missing-direction DWI reconstruction, tensor-derived metrics, and principal
diffusion orientation estimation.
Read the full abstract ▾
All authors Zhibo Chen, Yajuan Huang, Yu Guan, Qiuyun Fan, Dong Liang, Qiegen Liu
Machine Learning · Cross-listed from stat.ML
From topology learning to graph generation: A unifying perspective
Xiaowen Dong, Hoi-To Wai, Siheng Chen et al. (+2 more)
Learning graph structures from data is a fundamental problem that spans a wide range of signal processing and machine learning tasks. While significant effort has been made to tackle the problem, existing research has largely evolved along two parallel directions. The first seeks to infer the
topology of an individual graph from observations supported on it, whereas the second seeks to learn a generative distribution from observed graph instances, enabling the sampling of new graphs. This review presents a unified framework that connects these formulations by viewing them as inverse problems of a common generation process for graph data. We review the major methodologies within this framework, highlight their relationships, strengths, and limitations, and identify opportunities for integrating ideas across paradigms. By bridging graph
topology learning and graph generation, this review provides a broader cross-disciplinary perspective on the field and outlines promising directions for future research.
Read the full abstract ▾
All authors Xiaowen Dong, Hoi-To Wai, Siheng Chen, Laura Toni, Dorina Thanou
Machine Learning
Entangled Representations Amplify Collateral Damage in Unlearning
Evžen Wybitul, Tim G. J. Rudner and Christian Schroeder de Witt
A long-held intuition in interpretability research is that representational
entanglement, the sharing of structure between knowledge domains in a neural network, makes unlearning harder. While the intuition is widespread, it has never been directly tested in a controlled experiment. We present a way to do so: by repurposing Selective Gradient Masking (SGTM), we train a suite of six 254M-parameter
language models on English Wikipedia with graded levels of disentanglement between biology and non-biology knowledge. Applying three standard unlearning methods to every model in the suite, we find that more disentangled models consistently achieve better retain-forget trade-offs: at a fixed level of forgetting, the most disentangled models incur roughly $4\times$ lower retain cost under two of the three methods, and $1.3\times$ lower under the third. Because our intervention changes only the model, not the data or the unlearning
algorithm, this is direct evidence that representational
entanglement is one of the causes of collateral damage in unlearning, as interpretability researchers have long suspected. A similar design could be used to test other structural claims from interpretability.
Read the full abstract ▾
Computer Vision
RouteGraph-Mona: Confusion-Aware Routing Fine-Tuning for Mineral Image Classification
Jierui Li, Zhiyuan Qi, Hao Zhu et al. (+7 more)
Mineral image classification is important for geological exploration and resource development, but it remains challenging due to substantial intra-class variations in appearance and high inter-class visual similarity. Multi-cognitive Visual Adapter (Mona) is a
vision-oriented parameter-efficient adapter that adapts pre-trained visual models by tuning only a few parameters. However, Mona statically aggregates responses from multiple scales, limiting its ability to accommodate sample-specific scale preferences and model confusion among visually similar mineral categories. To address this issue, we propose RouteGraph-Mona, a lightweight route-space regularization method built on Mona. Specifically, we replace Mona's static multi-scale aggregation with sample-adaptive routing. The resulting branch-selection behavior defines a compact routing space that captures each image's scale preferences. We then regularize the resulting routing signatures with class-wise route anchors and confusion-weighted margins. The route anchors encourage class-consistent routing patterns, while the margins promote greater separation between visually similar categories in the routing space. Experiments on three public mineral image
datasets with two visual backbones show that RouteGraph-Mona consistently outperforms Mona in mean accuracy and remains competitive with representative fine-tuning methods and mineral image classification baselines.
Read the full abstract ▾
All authors Jierui Li, Zhiyuan Qi, Hao Zhu, Yufan Liu, Jixian Liu, Shaojie Jiang, Jianda Wang, Yaqi Liu, Xiaotong Li, Wei Wang
Sound
Auditory Illusion Benchmark for Large Audio Language Models
Hayoon Kim, Eunice Hong and Kyogu Lee
Perceptual illusions have long served as crucial probes into human cognition, revealing biases and limitations of perception. In the auditory domain, such illusions provide a unique lens for testing whether Large Audio
Language Models (LALMs) replicate human perceptual tendencies. Despite their importance, most
benchmarks focus on visual illusions or general audio tasks, leaving auditory illusions underexplored. To this end, we present AIB, the first auditory illusion
benchmark for LALMs, covering ten representative illusions across music, sound, and
speech, each annotated for the presence of knowledge-based priors. Our methodology pairs model evaluation with controlled human listening studies, enabling direct comparison of responses. Results show systematic differences: while most LALMs remain signal-faithful on low-level acoustic illusions, several exhibit more human-like responses when linguistic or musical priors are involved, although no model matches the human perceptual profile. These findings highlight the current limitations of LALMs as cognitive models. By establishing auditory illusions as a rigorous testbed, our work offers a new perspective for probing neural black-box models and advancing understanding of auditory cognition. AIB is publicly available at https://github.com/gillosae/aib.
Read the full abstract ▾
Computation and Language
Do Large Language Models Capture the Diversity in their Training Data?
Youqi Wu and Farzan Farnia
Large
language models are trained to model conditional distributions over text, yet it remains inadequately understood whether they capture the full diversity of plausible outputs present in their training data. We study this question through an information-theoretic lens by comparing the conditional
entropy of model-generated outputs with that of the corresponding training data. Given paired input-output samples, we use conditional
entropy and its
matrix-based analogue based on von Neumann
entropy to measure output variability beyond what is explained by the conditioning input, without requiring multiple reference outputs for the same
prompt. Across LLM families with publicly available training data, including OLMo, Pythia, and GPT-Neo, we consistently find that model-generated outputs exhibit lower conditional
entropy than their training data, across different model scales, sequence lengths, and decoding strategies. We observe a similar conditional diversity gap beyond
language modeling, including class-conditioned ImageNet generators and text-conditioned models trained on MS-COCO. To address this gap, we propose a post-hoc correction mechanism that generates multiple outputs for each input and reweights them through a
matrix-
entropy projection, increasing conditional diversity while remaining close to the original model distribution. We prove the concavity of the
matrix-based conditional
entropy functional, which makes the resulting
entropy-constrained projection a convex optimization problem, and develop a scalable mirror-descent
algorithm for its implementation. Our results reveal a systematic conditional diversity gap between modern generative models and their training data, and provide an information-theoretic framework for measuring and mitigating this gap.
Read the full abstract ▾
Artificial Intelligence
CoMerge: Conflict-Driven Preference Optimization for Multi-Task Model Merging
Mingjie Zheng, Zihao Chen, Wenqing Chen et al. (+4 more)
Model merging provides an efficient paradigm for constructing multi-task large
language models (LLMs) without full model retraining, yet it remains challenged by parameter interference. While existing methods aim to preserve the capabilities of individual expert models and mitigate interference, they generally do not directly learn from the potentially degraded behaviors exposed by naive merging. In this paper, we propose a conflict-driven preference optimization framework for model merging (CoMerge), which reformulates model merging as a preference optimization problem. The approach utilizes a self-supervised, conflict-driven strategy that leverages the defects of naive merging methods (e.g., task arithmetic) as hard negative samples to construct preference pairs without external annotations. By applying preference optimization to refine lightweight, tensor-wise merging coefficients, CoMerge enables the model to mitigate parameter-space conflicts while preserving task-specific capabilities. Extensive experiments show that CoMerge achieves an average normalized performance of 0.9968 on MergeBench, outperforming all evaluated data-free and data-driven model-merging baselines. Furthermore, on Llama-3.1-8B-Instruct, CoMerge yields marked improvements on conflict-sensitive tasks such as instruction following and safety, while remaining highly competitive with full-parameter fine-tuning despite optimizing only 1,445 scalar coefficients.
Read the full abstract ▾
All authors Mingjie Zheng, Zihao Chen, Wenqing Chen, Weile Yuan, Zhixuan Chu, Jianxing Yu, Zibin Zheng
Computation and Language
PaperCompiler: Faithful Paper-to-Code Generation via Repository-Level Specification Compilation
Yunhao Liu, Hong Phuc Pham and Jaehong Yoon
Faithfully translating research papers into repository-level implementations remains challenging because papers often describe methods at a high level, leave implementation assumptions implicit, and require generated repositories to preserve method logic, evaluation protocols, and cross-file consistency. Despite recent advances in paper-to-code
agents, their intermediate outputs are often presented as free-form plans or summaries that downstream coding
agents may ignore, reinterpret, or compress, leading to algorithmic simplification and inconsistent repository structure. To address these challenges, we introduce PaperCompiler, a paper-to-code generation framework that compiles paper-grounded evidence into explicit repository-level implementation specifications. PaperCompiler grounds implementation-relevant evidence while preserving source provenance and distinguishing paper-supported, inferred, externally delegated, and unresolved information. The resulting specifications encode non-degradation requirements, ownership assignments, cross-file dependencies, and file-level constraints. Repository generation proceeds under these compiled specifications while retaining flexibility over local engineering choices not fixed by the paper. PaperCompiler outperforms strong baselines on Paper2CodeBench, achieving a 13.8% relative improvement in reference-based fidelity (from 3.64 to 4.15) and reducing high-severity evaluator critiques (from 13.2% to 6.1%).
Read the full abstract ▾
Robotics
CrashDiffuser: VLM-Guided Collision Intent Reasoning for Fine-Grained Safety-Critical Traffic Scenario Generation
Shucheng Zhang, Yuang Zhang, Bingzhang Wang et al. (+3 more)
Generating safety-critical scenarios is essential for evaluating autonomous driving systems. However, existing generators primarily focus on inducing collisions and offer limited control over where contact occurs on the target vehicle. In this paper, we study fine-grained safety-critical scenario generation, where success requires both a target collision and a specified head, rear, or side contact region. We propose CrashDiffuser, a closed-loop VLM-guided
diffusion framework that decouples semantic collision
reasoning from continuous trajectory synthesis through a hierarchical collision-intent interface derived from the requested target contact region. At initialization, the VLM extracts reusable scene-level context; at each replanning step, it predicts a structured action tuple describing speed change, turning behavior, and collision stage. This intent conditions a
diffusion model to generate executable
adversarial trajectories, while collision-guided sampling, candidate selection, and short-horizon replanning adapt generation to the target vehicle's evolving behavior. On WOMD-derived closed-loop scenarios, CrashDiffuser achieves a target-collision rate of 50.33% in a single attempt and 67.98% after three attempts, together with a contact-region control success rate of 40.05% and competitive trajectory naturalness. Component ablations further support the proposed design.
Read the full abstract ▾
All authors Shucheng Zhang, Yuang Zhang, Bingzhang Wang, Muhammad Monjurul Karim, Kehua Chen, Yinhai Wang
Cryptography and Security
Retrosynthesis of Synthetic Media for Explainable AI Provenance Forensics
Yijie Lin, Ching-Chun Chang, Isao Echizen et al. (+2 more)
With the rapid proliferation of generative models on Machine Learning as a Service (MLaaS) platforms, reliably tracing the provenance of synthetic media without modifying generator architectures or parameters remains a major challenge. In this work, we propose a self-referential retrosynthesis framework for explainable AI provenance forensics under a fixed-generator setting. The framework leverages a jointly optimized encoder-decoder pair to implement a self-
embedding mechanism that enables round-trip consistency verification. During inference, client inputs are first encoded and then processed by the generator to produce outputs with high visual fidelity. For forensic verification, the consistency between the resynthesized image and the query image is analyzed to determine whether the image originates from the target generative model. Our approach eliminates the need for watermark
embedding or modifications to the generation process. Experimental results show that images generated from encoded inputs maintain visual quality comparable to original generator outputs, while decoded images reliably trace back to their corresponding source inputs. Furthermore, the framework provides interpretable evidence for generative content provenance, establishing a practical tool for explainable generative AI forensics.
Read the full abstract ▾
All authors Yijie Lin, Ching-Chun Chang, Isao Echizen, Hui Li, Chin-Chen Chang
Computer Vision
MAOL: Morphology-Aware Ordinal Learning for Fine-Grained Industrial Defect Severity Grading
Zhaoyang Wang, Haiyong Chen, Binyi Su et al. (+4 more)
Fine-grained defect severity grading is essential for industrial inspection, yet remains challenging due to the ordinal nature of severity labels, the strong dependence on morphology-related cues, and the train-test discrepancy between clean annotated instances and noisy predicted instances in two-stage pipelines. We propose MAOL, a Morphology-Aware Ordinal Learning framework for fine-grained industrial defect severity grading. MAOL formulates severity grading as an instance-level ordinal learning task, incorporates explicit morphological features to enhance representation learning, introduces class-conditional adaptive ordinal thresholds to model defect-specific grading boundaries, and employs prediction-aware training via localization perturbation to improve robustness to imperfect predicted instances. Extensive experiments under both clean-ROI and predicted-instance settings demonstrate that MAOL consistently outperforms rule-based methods, nominal classification models, and existing ordinal baselines, especially in the predicted-instance setting. The proposed approach ranked third in the IDA 2026 Challenge on Fine-Grained Severity Grading for High-Precision Manufacturing.
Read the full abstract ▾
All authors Zhaoyang Wang, Haiyong Chen, Binyi Su, Kun Liu, Kun Wang, Xianen Zhou, Atik Shahariar
Machine Learning
CAPTURE: Disentangling Preference Drift from Memory Poisoning in Personalized LLM Agents
S M Asif Hossain, Ruksat Khan Shayoni and Md Kishor Morol
Personalized
language agents use persistent
memory to adapt to users over time, but the same mechanism creates an attack surface. When new information conflicts with stored preferences, an
agent must distinguish genuine preference drift from temporary context shifts, ambiguity, or
adversarial memory poisoning. We formulate this problem as a continuous-time partially observable decision process over a latent user state and show why rules based only on recency and provenance are insufficient. CAPTURE addresses this ambiguity with a neural differential-equation belief tracker, a multi-timescale
memory ledger, uncertainty-triggered clarification, and counterfactual
auditing of cited
memories. On 480 held-out episodes from 96 users, CAPTURE achieves a 71.5% win rate, compared with 69.3% for an identically supervised baseline and 66.1% for the strongest heuristic baseline. It limits fixed-policy poisoning success to 11.5% while accepting 83.5% of genuine preference updates. Under an adaptive attacker with access to the released weights, attack success rises to 24.7%, exposing a real adaptation-security tradeoff. We further evaluate the frozen system zero-shot on an independently constructed
benchmark and replay longitudinal interaction histories from 40 users collected over two to three weeks. These results suggest that modeling preference authenticity explicitly can improve both personalization and robustness in
memory-augmented LLM
agents.
Read the full abstract ▾
Artificial Intelligence
Codebook Agent: Amortized Topology Design for LLM Multi-Agent Systems
Jinxi Yu, Yubei Li, Eric Hanchen Jiang et al. (+6 more)
Adapting the communication
topology of an LLM multi-
agent system to each query improves both accuracy and efficiency, yet current designers treat this as conditional graph generation: a variational, autoregressive, or
diffusion decoder searches the $N \times N$ adjacency space, and a graph-network proxy trained on utility and a structural cost such as edge count ranks the sampled candidates. We argue that this formulation is misaligned with the problem. Empirically,
topologies that survive a reward filter collapse to about six distinct graphs even when the codebook capacity grows from 8 to 64; edge count is negatively correlated with measured
token consumption (Pearson $r \approx -0.4$), so sparsifying the graph makes inference more expensive; and a message-passing scorer over
agent-profile nodes is adjacency-invariant whenever
agents share a profile—the default configuration of published
benchmarks—so it cannot rank candidates at all in that regime. These three facts motivate Codebook
Agent: a vector-quantized autoencoder compresses successful
topologies into a query-independent 16-entry codebook; a reward-weighted MLP maps the query
embedding to a distribution over codes; and an MLP proxy that reads the flattened adjacency, regressed on measured utility and per-task normalized
token cost, reranks the top decoded candidates in a single batched forward pass. With no iterative search and no message passing at test time, Codebook
Agent is the most accurate method on all six
benchmarks we compare (84.6 average against 83.0 for the strongest prior designer), emits a
topology in 2.4 ms, and uses 21.9–33.2% fewer LLM
tokens.
Read the full abstract ▾
All authors Jinxi Yu, Yubei Li, Eric Hanchen Jiang, Zhi Zhang, Dong Liu, Wenxiao Zhao, Levina Li, Kai-Wei Chang, Ying Nian Wu
Social and Information Networks
From Detection to Characterization: A Large-Scale Study of Ragebait on Japanese X
Zhiyang Qi, Kazuhiro Ito, Jinghui Chen et al. (+5 more)
Ragebait refers to online content intentionally designed to provoke anger or outrage and thereby increase
attention and engagement. However, reliable large-scale detection and systematic analysis of ragebait remain limited, hindering efforts to understand its prevalence, impact, and mitigation. This study aims to develop an effective ragebait detection framework and to clarify the characteristics of ragebait at scale, providing a basis for understanding and mitigating emotionally provocative content online. We constructed a labeled
dataset with the assistance of a large
language model (LLM) and trained several Japanese
language models for ragebait detection. The resulting ensemble classifier was then applied to a large-scale
dataset of Japanese-
language posts on X. Our analysis shows that ragebait is more prevalent in politically and socially contentious topics, including politics, discrimination, public health, and interpersonal conflict. Ragebait posts also spread faster and receive more negative reactions than non-ragebait posts, particularly anger, fear, disgust, sadness, and surprise. These findings demonstrate the utility of the proposed detector and provide a large-scale characterization of ragebait in Japanese online discourse.
Read the full abstract ▾
All authors Zhiyang Qi, Kazuhiro Ito, Jinghui Chen, Hibiki Nakamura, Zhangxuan Chen, Erina Murata, Masaki Chujyo, Fujio Toriumi
Numerical Analysis
Scattered data interpolation on the torus by compactly supported multinode Shepard operators
F. Dell'Accio, F. Di Tommaso, R. Lammirato et al. (+1 more)
We introduce a compactly supported multinode Shepard operator for the interpolation of scattered data on the
torus embedded in $\mathbb{R}^3$. The method combines local
polynomial interpolation of total degree $d\in \mathbb{N}$ with compactly supported Shepard-type weights, so that the approximation at each evaluation point depends only on neighbouring stencils of nodes. The
torus is treated as an algebraic surface defined by a quartic
polynomial, and Gröbner bases are used to construct reduced
polynomial spaces on the surface by removing the redundancy induced by the defining equation. This yields local Vandermonde systems adapted to the toroidal geometry. We discuss the metric structure of the
torus, show the local equivalence between the periodic parameter distance and the Euclidean distance inherited from $\mathbb{R}^3$, and use this equivalence to motivate the compact support construction. We establish a uniform error estimate in terms of the maximal support radius and the local Lebesgue constants. Under uniform locality and stability assumptions, the method converges with order $d+1$ with respect to the fill distance. Numerical experiments on analytical test functions confirm
polynomial reproduction and exhibit an error decay consistent with the theoretical analysis. The approach is also tested on Computational Fluid Dynamics data mapped onto the
torus, including the interpolation of the velocity components, the reconstruction of the velocity magnitude from the interpolated components, and the reconstruction of a tangent velocity field through an orthonormal lifting of the interpolated components.
Read the full abstract ▾
All authors F. Dell'Accio, F. Di Tommaso, R. Lammirato, F. Larosa
Computer Vision
T2LSC-Bench: Benchmarking Localized Semantic Control in Text-to-Image Generation
Yan Wang, Xinyi Hou, Weiguo Lin et al. (+2 more)
Recent text-to-image models have become increasingly capable of rendering explicit text, but reliable localized text control requires more than generating the correct string. In applications such as product labeling, signage, and interface design, target text should be rendered within a designated text-bearing region without altering the predefined subject identity or surrounding scene semantics. We refer to violations of this requirement as target-text-associated semantic leakage, in which target-text semantics are expressed through non-textual visual content beyond the designated anchor. Existing visual-text
benchmarks primarily evaluate readability, spelling accuracy, and layout, leaving this form of semantic leakage largely unexamined. We introduce T2LSC-Bench, a controlled diagnostic
benchmark comprising 50 seed subjects and 1,200
prompt cases per model, yielding 7,160 evaluated images across six models. Its factorized design varies semantic relation, scene openness,
prompt mode, and
language. A dual-branch protocol combines OCR-VLM text verification with structured VLM semantic judgments to measure Text-at-Anchor Accuracy (TAA), Semantic Subject Preservation (SSP), Semantic Leakage Rate (SLR), and Conditional Semantic Leakage Rate (cSLR). Under stress-test conditions, SLR increases from 1.2% to 18.1% and cSLR from 1.3% to 18.2%, whereas TAA decreases only from 91.4% to 90.9%. Anti-leakage prompting reduces SLR from 16.6% to 8.4% without degrading rendering accuracy. Human validation on 420 images shows strong agreement between automatic and adjudicated annotations. These results show that accurate text rendering does not guarantee local containment of target-text semantics.
Read the full abstract ▾
All authors Yan Wang, Xinyi Hou, Weiguo Lin, Junjun Si, Siwei Ma
Artificial Intelligence
APEx: Distillation of Agent Procedural Experience for Adaptive Deep Research Question Answering
Jie Ding, Rui Sun, Xinyuan Zhang et al. (+2 more)
Deep research
agents augment large
language models with external tools to answer complex, long-horizon questions through multi-turn
reasoning. Learning from prior experience is crucial for continual improvement, yet existing methods either retrieve verbose task-specific traces that burden decision-making, or distill procedural skills that remain decoupled from downstream policy adaptation. We propose APEx, a hierarchical experience utilization framework that organizes interaction history into instance-level trajectory
memories and category-level procedural skills, and couples them through a closed-loop architecture of Executor, Distiller, and Planner. The three modules are optimized via a three-stage alternating GRPO training paradigm, enabling reward-guided skill
distillation rather than fixed-
prompt generation. At test time, distilled skills serve as procedural priors for online Planner adaptation through skill-guided test-time reinforcement learning, allowing ground-truth-free self-improvement with skill-
alignment regularization to prevent policy drift. Experiments on 7
benchmarks demonstrate that APEx achieves state-of-the-art performance, surpassing GPT-5.4 by 14.7 points and the strongest
memory-augmented baseline by 3.0 points.
Read the full abstract ▾
All authors Jie Ding, Rui Sun, Xinyuan Zhang, Zeyu Zhang, Xin Liu