arXiv
NeuronEye: Query-Guided Visual Concept Activation for Vision-Language Reasoning
Current vision-language models (VLMs) encode visual information in dense hidden states where object identity, spatial...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
arXiv
Correct Answers, Invalid Traces: What Verifiable Grade-School Math Reveals About Chain-of-Thought Traces
Chain-of-thought traces are widely read as records of how models reach their answers, informing debugging, agent audi...
arXiv
Do LLM Agents Execute the Plans They Declare? From Planning-Mode Declaration to Pattern-Specific Execution
Large language models (LLMs) enable agents to solve long-horizon tasks by generating a plan and then executing it in ...
arXiv
How Local Mixing Encodes Relative Position in Global NoPE Attention
The attention operation is naively position invariant. However, positional information is fundamental to natural lang...
arXiv
Stochastic World Models for Verifying Vision-Based Neural Feedback Systems
Verifying a vision-based neural feedback system requires a model of the observations its controller acts upon. Such a...
arXiv
Breaking the Uniformity Trap: Scaling Video Diffusion Model via SplitMoE
Mixture-of-Experts (MoE), popularized by large language models, is a promising paradigm for scaling visual generative...
arXiv
AdviSD: Learning to Advise Frontier LLMs via Targeted Multi-Turn Self-Distillation
A small trainable advisor can steer a frozen language-model executor using natural-language advice. In addition to le...
arXiv
Learning Meta-Skills for Agent Harness Design in Test-Time AI4AI
Agent performance depends on both reasoning ability and the environment in which it acts. We study test-time AI-for-A...
arXiv
Thinking Before Thinking: Scaling Agentic Inference Through Meta-Reasoning
As agents take on longer and more complex problems, controlling the execution becomes a task in its own right. Each s...
arXiv
Beyond the Timeline: Augmenting Long-Video Memory with Grounded Entity Biographies
Answering questions about long videos often requires connecting events involving the same objects across hours or day...
arXiv
LeapQuant: Efficient Linear Attention with Accurate Recurrent State Quantization
Recent LLMs increasingly adopt hybrid designs that replace standard attention with linear attention, such as Gated De...
arXiv
STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization
Linear attention replaces growing KV caches with fixed-size recurrent states, yet these persistent states can become ...