Found 26 document(s)
Page 1 of 2
-
Humans reason about the physical world by flexibly combining different forms of inference as a problem unfolds. Achieving this flexibility is a major open challenge in AI: capabilities often remain separated across speci...
-
Websites and applications deploy CAPTCHAs and anti-automation mechanisms that use behavioral signals such as interaction trajectories and timing, not outcomes alone, to distinguish humans from automated agents. We call t...
-
The interest in leveraging physics-based inductive bias in deep learning has resulted in recent development of hybrid deep generative models (hybrid-DGMs) that integrate known physics-based mathematical expressions in ne...
-
Generative recommendation with semantic IDs represents each item as a sequence of discrete codes derived from its semantic representation and predicts these codes to generate recommendations. Existing semantic-ID recomme...
-
Training generalizable embodied agents requires realistic, varied, and simulation-ready indoor environments. Language-guided methods support semantic planning and object-level reasoning, but precise spatial grounding rem...
-
Masked patch self-distillation is a key component of modern vision foundation models, including DINOv2 and DINOv3, yet its implications for local visual information remain unclear. We show that its semantic benefits can ...
-
Automatic DJ systems mostly target electronic dance music, whose regular structure makes rule-based mixing relatively easier. Vocal-rich popular music is harder: which track to play next, where to cue it, and which trans...
-
While Multimodal Large Language Models (MLLMs) excel at zero-shot reasoning, their spatial capabilities are primarily evaluated through static, passive observation. In complex, human-centric scenes, occlusion often hides...
-
Broken access control (BAC) ranks among the most severe web-application vulnerability classes, yet its automated repair remains largely unexplored. Unlike memory-safety vulnerabilities, BAC is a logic vulnerability whose...
-
Knowing when they are reliable is essential for language models to support human-AI collaboration. Yet interaction feedback is not always complete or correct, and may mislead models' understanding of their own capabiliti...
-
From Belief Inference to Task Action: A Multi-Level Evaluation of Theory of Mind on Verifiable TasksEffective collaboration requires language models to understand what others know and believe, and to act accordingly. Models that assume others share their information may omit necessary communication and undermine coordi...
-
Mass formulas for prescribed hull dimensions have mainly been studied for linear codes viewed as subspaces of the whole space. We study internal enumeration for an arbitrary fixed parent code. Let $C$ be an $[n,k]_q$ lin...
-
Reasoning models trained with Group Relative Policy Optimization (GRPO) now produce chains of thought thousands of tokens long, and recent studies reveal that such training is prone to policy collapse. Entropy regulariza...