arXiv:2508.12026v2 Announce Type: replace-cross Abstract: Bongard Problems (BPs) provide a challenging testbed for abstract visual reasoning (AVR), requiring models to identify visual concepts fromjust a few examples and describe them in natural language. Early BP benchmarks featured synthetic black-and-white drawings,…
arXiv:2602.16823v1 Announce Type: new Abstract: *Automated circuit discovery* is a central tool in mechanistic interpretability for identifying the internal components of neural networks responsible for specific behaviors. While prior methods have made significant progress, they typically depend on heuristics or…
arXiv:2602.15852v2 Announce Type: replace-cross Abstract: Clinical natural language processing (NLP) models have shown promise for supporting hospital discharge planning by leveraging narrative clinical documentation. However, note-based models are particularly vulnerable to temporal and lexical leakage, where documentation artifacts encode future…
arXiv:2602.16826v1 Announce Type: new Abstract: Theory of mind (ToM) enables AI systems to infer agents’ hidden goals and mental states, but existing approaches focus mainly on small human understandable gridworld spaces. We introduce HiVAE, a hierarchical variational architecture that scales…
arXiv:2602.16979v1 Announce Type: cross Abstract: Despite the recent success of Multimodal Large Language Models (MLLMs), existing approaches predominantly assume the availability of multiple modalities during training and inference. In practice, multimodal data is often incomplete because modalities may be missing,…
arXiv:2602.16829v1 Announce Type: new Abstract: When feedback is absorbed faster than task structure can be evaluated, the learner will favor feedback over truth. A two-timescale model shows this feedback-truth gap is inevitable whenever the two rates differ and vanishes only…
arXiv:2602.17211v1 Announce Type: cross Abstract: Generating samples from limited information is a fundamental problem across scientific domains. Classical maximum entropy methods provide principled uncertainty quantification from moment constraints but require sampling via MCMC or Langevin dynamics, which typically exhibit exponential…
arXiv:2602.16833v1 Announce Type: new Abstract: Exploration remains a key bottleneck for reinforcement learning (RL) post-training of large language models (LLMs), where sparse feedback and large action spaces can lead to premature collapse into repetitive behaviors. We propose Verbalized Action Masking…
arXiv:2602.17395v1 Announce Type: cross Abstract: Generalized Category Discovery (GCD) aims to identify novel categories in unlabeled data while leveraging a small labeled subset of known classes. Training a parametric classifier solely on image features often leads to overfitting to old…
arXiv:2602.16837v1 Announce Type: new Abstract: Transformer models systematically favor certain token positions, yet the architectural origins of this position bias remain poorly understood. Under causal masking at infinite depth, prior theoretical analyses of attention rollout predict an inevitable collapse of…
