arXiv
Interpretable AI predicts a 2026 summer dry anomaly in central China
Seasonal precipitation anomalies are largely regulated by atmospheric circulation, which dynamical models predict wit...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
arXiv
Finetuning Strategies for Querying Sounds by Vocal Imitation
This technical report describes our winning submission to the AES AIMLA 2025 Challenge on querying sound effects by v...
arXiv
Beyond Teacher Likelihood: Group-Calibrated On-Policy Distillation for Long-Context Reasoning
On-policy distillation (OPD) trains a student on its own responses using dense token-level guidance from a stronger t...
arXiv
ADEPT: Accelerating Dexterity via Pre-Training and Post-Training using Reinforcement Learning
We introduce Accelerating Dexterity via Pre-Training (ADEPT), a large-scale reinforcement learning (RL) framework for...
arXiv
SPADE: Self-Play in Adaptive Synthetic Executable Environments
Continuous self-improvement requires an ever-expanding pool of self-generated, diverse, adaptive goals. For language ...
HuggingFace
SkillForge: Self-Distilling Agents for Project-Specific Issue Resolution
Large language model (LLM) based agents have demonstrated remarkable proficiency in automated software issue resoluti...
HuggingFace
FM-Bench: A Benchmark for Long-Horizon Management with Competing Agents
Language model agents now execute bounded tasks reliably. Whether they can sustain effective decision-making over lon...
HuggingFace
Looped Language Models Improve Compositional Tool Calling
Looped language models have shown promising results on reasoning benchmarks, yet their potential for agentic tool use...
HuggingFace
SPADE: Self-Play in Adaptive Synthetic Executable Environments
Continuous self-improvement requires an ever-expanding pool of self-generated, diverse, adaptive goals. For language ...
HuggingFace
SemaPLC: A Project-Grounded, Verification-Gated Agent Harness for PLC Code Generation
Programmable logic controllers (PLCs) run industrial plants, and large language models can already generate independe...
HuggingFace
Training Chemical Plausibility-Aware Large Language Models for Single-Step Retrosynthesis
Single-step retrosynthesis is a central component of computer-aided synthesis planning, yet its intrinsically one-to-...
HuggingFace
Training Leaves Traces: Centered Residual Signatures for Language Model Lineage Verification
Open-weight language models are fine-tuned, quantized, pruned, and merged, yet their provenance is often undocumented...