arXiv
ALER-TI: Aligned Latent Embedding Retrieval for Time Series Imputation
Deep learning has significantly advanced time series imputation, yet most existing architectures primarily rely on lo...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
arXiv
RL Post-Training Builds Compositional Reasoning Strategies
Does RL post-training merely amplify primitive skills already latent in a base model, or can it compose primitive ski...
arXiv
Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops
AI systems increasingly participate in their own improvement: revising their outputs, adapting their own harnesses du...
arXiv
DiaLLM: An Investigation into the Robustness-Generation Gap in English Dialect Adaptation
Large language models increasingly \emph{understand} dialectal English, yet still \emph{produce} only standard, US-le...
arXiv
SkillCenter: A Large-Scale Source-Grounded Skill Library for Autonomous AI Agents
Autonomous AI agents can execute complex tasks with limited human review, yet they often lack the grounded operationa...
arXiv
Agon: Competitive Cross-Model RL with Implicit Rival Grading of Reasoning
Reinforcement learning from verifiable rewards (e.g. GRPO) is the engine behind today's reasoning models, yet it grad...
arXiv
Selective Timestep Weighting and Advantage-Based Replay for Sample-Efficient Diffusion RLHF
Reinforcement learning from human feedback (RLHF) has emerged as a powerful paradigm for aligning generative models w...
arXiv
Institutional Red-Teaming: Deployment Rules, Not Just Models, Causally Shape Multi-Agent AI Safety
We introduce institutional red-teaming, an evaluation methodology for testing deployment rules in multi-agent AI: hol...
arXiv
Breaking Database Lock-in: Agentic Regeneration of High Performance Storage Readers for Database Bypass
Analytical workloads operating on data stored in external database systems face a fundamental bottleneck: data access...
arXiv
Co-LMLM: Continuous-Query Limited Memory Language Models
Limited memory language models (LMLMs) externalize factual knowledge during pretraining to a knowledge base (KB), rat...
arXiv
Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning
Structure-property relationships are foundational to biology, chemistry and materials science, where function, reacti...
HuggingFace
Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence
Despite the recent promise in robot control, video generative models suffer from a domain mismatch due to their prima...