arXiv
LLM Detection as an Intervention: Downstream Impact under Strategic User Behavior
As LLM adoption becomes more widespread, there is a growing interest in detecting LLM-generated content, for example ...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
arXiv
Riemannian Deep Learning:Modules, Networks, and Geometries
Deep neural networks on manifold-valued representations have attracted growing interest, but many basic components re...
arXiv
From Distances to Trajectories: Real-Time Signed Distance Function Mapping and Distance-Accelerated Motion Planning for UAVs
Autonomous flight in cluttered environments requires a robot to build a geometric map of its surroundings and plan sa...
arXiv
Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information
Reinforcement learning with verifiable rewards (RLVR) improves reasoning in large language models. Yet, typical RLVR ...
arXiv
ResearchArena: Evaluating Sabotage and Monitoring in Automated AI R&D
As AI agents begin to automate AI R&D, we need ways to assess whether their outputs are safe to deploy, even when the...
arXiv
Associative Emotional Learning in Convolutional Neural Networks
Associative emotional learning enables organisms to adaptively link pleasant or unpleasant outcomes to the presence o...
arXiv
ISO: An RLVR-Native Optimization Stack
Reinforcement learning with verifiable rewards (RLVR) is rapidly advancing the reasoning capabilities of language mod...
arXiv
Provable diffusion-based posterior sampling for linear inverse problems via DDIM
Diffusion-based methods have achieved remarkable empirical success in solving inverse problems. However, many existin...
arXiv
Agents in the Wild: Where Research Meets Deployment
Agentic systems large language model (LLM) based architectures capable of reasoning, planning, acting, and coordinati...
arXiv
CodeRescue: Budget-Calibrated Recovery Routing for Coding Agents
Coding agents increasingly operate in executable environments where a failed attempt produces actionable feedback rat...
arXiv
Appearance Pointers -- Multimodal Region Control of Diffusion Transformers
Controllable image generation remains challenging for creative professionals, who often require precise regional cont...
arXiv
Copy Less, Ground More: Overcoming Repetitive Copying in Long-Context Reasoning via Evidence-Aware Reinforcement Learning
Large language models that generate step-by-step reasoning traces have achieved strong performance on complex tasks, ...