arXiv
PGFS++: Molecular Property Improvement under Synthesis and Diversity Constraints
Improving molecular properties, such as drug-likeness or binding affinity, is a recurring task in early-stage drug di...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
arXiv
Tuning the Stochastic Machine: A Systems Engineer's Operating Model for Human-AI Engineering
When an expert corrects an LLM assistant's error, the correction usually dies with the session, and the error class r...
arXiv
Leaf Values as Coordinates: Exact Contrastive Explanation for Gradient-Boosted Ensembles
A gradient-boosted ensemble predicts by summing one leaf value per tree. Read those values as coordinates rather than...
arXiv
Grouping the Stochastic Machine: Precision, Not Capability, as the Frontier Metric for AI Systems
Frontier language models are compared, marketed, and benchmarked on capability -- what their best or average output c...
arXiv
Pre-Compiled Pipeline Shards for Distributed LLM Inference on Intel AI PC Fleets
Modern Intel AI PCs ship capable integrated GPUs and NPUs with 16+ GB of unified memory, and they spend considerable ...
arXiv
Beyond the Transcript: Detecting Covert Co ordination in Latent Multi-Agent Communication
Language-model agents can communicate through continuous hidden states that are invisible in public transcripts, crea...
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...
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...