arXiv
Diagnosing Dense Same-Class Attribute Misbinding in Large Vision-Language Models
Large vision-language models can recognize the objects and attributes in a crowded scene yet assign an attribute to t...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
arXiv
When State Becomes an Attack Surface: State-Semantic Injection in LLM-Driven Embodied Agents
Large Language Models (LLMs) have demonstrated capabilities in in-context learning, task decomposition, step-by-step ...
arXiv
Quipu: A Governed Bitemporal Knowledge Graph Store
Agents now write knowledge graphs, but knowledge-graph stores still carry defaults set when humans curated them: acce...
arXiv
CaliBench: Are the Stochastic Dynamics of Video World Models Physically Calibrated?
Video world models approximate the stochastic distribution of physical outcomes through generative sampling, but exis...
arXiv
Policy Iteration with Human Feedback: Bringing Post-Training RL to In-context Learning
Generative pretraining established reusable task representations; later work on language-based task conditioning and ...
arXiv
Model Hypnosis: Strong control of AI via additive subliminal effects
We demonstrate that AI models are broadly susceptible to a phenomenon we call model hypnosis, in which individually w...
arXiv
HAF: Adapting Generalist VLAs to Humanoid Whole-Body Loco-manipulation via Hierarchical Action Flow and Spectral Latent RL
Humanoid robots hold great promise as general-purpose agents in human-centered environments, yet generalist vision-la...
arXiv
Proteus: Incremental Memory Activation for Long-Context Sequence Modeling
The quadratic cost of attention-based sequence models for long contexts has motivated a growing line of research on m...
arXiv
What Do Compliance Detectors Read? An Audit of Activation Probes and Guard Models
Regulatory compliance monitoring in deployed language models is increasingly implemented as a legal and audit control...
arXiv
Towards Computational Provenance: Carrying Causal-State Evidence in Generated Text
A language model's output does not by itself provide verifiable evidence about the internal computation that produced...
arXiv
AutoSR: Automatic Symbolic Regression by Searching Research States
We introduce Automatic Symbolic Regression (AutoSR), a fully automated system that instantiates Research-Space Symbol...
arXiv
Improving the matrix multiplication exponent with modern optimization and AlphaEvolve
The current best bounds on the matrix multiplication exponent $ω$ are obtained through a refinement of the laser meth...