arXiv:2502.02390v3 Announce Type: replace-cross Abstract: Research on LLM technologies is rapidly emerging, with most of them employ a ‘fast thinking’ approach to inference. Most LLMs generate the final result based solely on a single query and LLM’s reasoning capabilities. However,…
arXiv:2511.10484v1 Announce Type: cross Abstract: Type 2 Diabetes Mellitus (T2DM) is a chronic metabolic disease that affects millions of people worldwide. Early detection is crucial as it can alter pancreas function through morphological changes and increased deposition of ectopic fat,…
arXiv:2511.10643v1 Announce Type: cross Abstract: Black-box distillation creates student large language models (LLMs) by learning from a proprietary teacher model’s text outputs alone, without access to its internal logits or parameters. In this work, we introduce Generative Adversarial Distillation (GAD),…
arXiv:2511.09768v1 Announce Type: new Abstract: Operationalizing definitions of fairness is difficult in practice, as multiple definitions can be incompatible while each being arguably desirable. Instead, it may be easier to directly describe algorithmic bias through ad-hoc assumptions specific to a…
arXiv:2511.10316v1 Announce Type: cross Abstract: Three-dimensional reconstruction in scenes with extreme depth variations remains challenging due to inconsistent supervisory signals between near-field and far-field regions. Existing methods fail to simultaneously address inaccurate depth estimation in distant areas and structural degradation…
arXiv:2511.09682v1 Announce Type: new Abstract: Instilling reasoning capabilities in large models (LMs) using reasoning training (RT) significantly improves LMs’ performances. Thus Audio Reasoning Models (ARMs), i.e., audio LMs that can reason, are becoming increasingly popular. However, no work has studied…
arXiv:2511.09710v1 Announce Type: new Abstract: As large language model (LLM) based agents interact autonomously with one another, a new class of failures emerges that cannot be predicted from single agent performance: behavioral drifts in agent-agent conversations (AxA). Unlike human-agent interactions,…
arXiv:2511.09600v1 Announce Type: new Abstract: In this research note, we show the relationship between two non-admissible argumentation framework semantics: cogent and weakly admissible semantics. We prove that, while cogent extensions are weakly admissible, the converse is not true.
arXiv:2511.09575v1 Announce Type: new Abstract: Reasoning is an essential component of human intelligence in that it plays a fundamental role in our ability to think critically, support responsible decisions, and solve challenging problems. Traditionally, AI has addressed reasoning in the…
arXiv:2511.09572v1 Announce Type: new Abstract: AI agents increasingly rely on external tools to solve complex, long-horizon tasks. Advancing such agents requires reproducible evaluation and large-scale training in controllable, diverse, and realistic tool-use environments. However, real-world APIs are limited in availability,…
