arXiv:2605.16654v1 Announce Type: cross Abstract: Manner and result verbs encode different aspects of event structure and have been discussed in developmental work as a potentially informative distinction for studying early verb learning. However, this distinction remains difficult to measure at scale because large annotated resources for manner and result classification are not currently available. We […]
Discovering interpretable low-dimensional dynamics using maximum entropy
arXiv:2605.16724v1 Announce Type: new Abstract: Models (i.e., governing equations) are fundamental to science and engineering. Advances in data acquisition now make it possible to extract interpretable, low dimensional descriptions from high dimensional observations. However, existing approaches sacrifice either interpretability for reconstruction accuracy or infer symbolic dynamics without relating latent coordinates to physically meaningful observables. Here […]
EmoMind: Decoding Affective Captions from Human Brain fMRI
arXiv:2605.16739v1 Announce Type: cross Abstract: Decoding visual experience from brain activity has advanced substantially, but cur- rent brain-to-text systems largely recover semantic content while discarding affect. Additionally, language models can generate emotional text when prompted with categorical labels, but such labels collapse rich inter-subject variability into coarse discrete bins. We present EmoMind, the first end-to-end […]
A Gene Ranking Framework Enhances the Design Efficiency of Genome-Scale Constraint-Based Metabolic Networks under Time Limits
arXiv:2511.03483v2 Announce Type: replace Abstract: The design of genome-scale constraint-based metabolic networks has steadily advanced, with an increasing number of successful cases achieving growth-coupled production, in which the biosynthesis of key metabolites is linked to cell growth. However, a major cause of design failures is the inability to find solutions within realistic time limits. Therefore, […]
Distinguishable Deletion: Unifying Knowledge Erasure and Refusal for Large Language Model Unlearning
arXiv:2605.16776v1 Announce Type: cross Abstract: Mitigating sensitive and harmful outputs is fundamental to ensuring safe deployment of LLMs. Existing approaches typically follow two paradigms: Knowledge Deletion (KD), which erases undesirable information during training, and Distinguishable Refusal (DR), which steers models away from using sensitive knowledge during inference. Despite rapid progress, KD-based unlearning struggles with biased […]
Baba in Wonderland: Online Self-Supervised Dynamics Discovery for Executable World Models
arXiv:2605.16725v1 Announce Type: new Abstract: Executable world models can be read, edited, executed, and reused for planning, but only if the program captures the environment’s transition law rather than semantic shortcuts in its surface vocabulary. We study online executable world-model learning under prior misalignment, where an agent must induce state-dependent dynamics from interaction evidence alone, […]
AgentKernelArena: Generalization-Aware Benchmarking of GPU Kernel Optimization Agents
arXiv:2605.16819v1 Announce Type: cross Abstract: GPU kernel optimization is increasingly critical for efficient deep learning systems, but writing high-performance kernels still requires substantial low-level expertise. Recent AI coding agents can iteratively read code, invoke compilers and profilers, and refine implementations, yet existing kernel benchmarks evaluate single LLM calls rather than full agent workflows, and none […]
Efficient Coding Predicts Synaptic Conductance
arXiv:2603.03347v3 Announce Type: replace Abstract: Synapses are information efficient in the sense that their natural conductance values convey as many bits per Joule as possible, but efficiency falls rapidly if the conductance is forced to deviate from its natural value (Harris et al, 2015. However, the exact manner in which efficiency falls as conductance deviates […]
PhysioSeq2Seq: A Hybrid Physiological Digital Twin and Sequence-to-Sequence LSTM for Long-Horizon Glucose Forecasting in Type 1 Diabetes
arXiv:2605.16860v1 Announce Type: cross Abstract: Accurate long-horizon glucose forecasting is critical for automated insulin delivery systems, which help people with type 1 diabetes (T1D) manage their glucose and avoid dangerous hypoglycemia. However, standard recursive long short-term memory (LSTM) networks suffer from systematic negative bias at longer horizons due to error compounding, while purely mechanistic ordinary […]
A Global-Local Graph Attention Network for Traffic Forecasting
arXiv:2605.16726v1 Announce Type: new Abstract: Traffic forecasting is a significant part of intelligent transportation systems. One of the critical challenges of traffic forecasting is to find spatio-temporal correlations. In recent years, graph convolutional networks and graph attention networks have replaced traditional statistical models to predict future traffic. However, it is complicated for both of them […]
Effort as Ceiling, Not Dial: Reasoning Budget Does Not Modulate Cognitive Cost Alignment Between Humans and Large Reasoning Models
arXiv:2605.16938v1 Announce Type: cross Abstract: Large Reasoning Models (LRMs) generate chain-of-thought traces whose length tracks human reaction times across cognitive tasks, but recent debate questions whether this alignment reflects genuine computational structure or surface verbosity. We test whether the alignment varies with inference-time reasoning effort. Across GPT-OSS-20B and GPT-OSS-120B, three effort levels, and six reasoning […]
Breaking $textitWinner-Takes-All$: Cooperative Policy Optimization Improves Diverse LLM Reasoning
arXiv:2605.11461v2 Announce Type: replace Abstract: Reinforcement learning with verifiers (RLVR) has become a central paradigm for improving LLM reasoning, yet popular group-based optimization algorithms like GRPO often suffer from exploration collapse, where the models prematurely converge on a narrow set of high-scoring patterns, lacking the ability to explore new solutions. Recent efforts attempt to alleviate […]