Research Papers
New Diagnostics and Action-Conditioned Objectives Improve Latent World Model Planning
Researchers propose diagnostics to measure whether latent distances reflect true task progress in JEPA-style world models, and int...
Hugging Face Researchers Introduce Top-K Prompting to Boost Diverse Retrosynthesis Predictions
A new study from Hugging Face presents Top-K prompting and plausibility-aware training for single-step retrosynthesis, achieving s...
New Data-Free Method Traces Language Model Lineage via Weight Signatures
Researchers introduce a passive, data-free technique that verifies whether open-weight language model checkpoints share ancestry b...
SPADE: Self-Play Framework Lets LLMs Design Their Own Training Environments
Hugging Face researchers introduce SPADE, a self-play reinforcement learning framework where a language model acts as both environ...
SemaPLC: Verification-Gated Agent Harness Boosts PLC Code Generation Reliability
SemaPLC, a new agent harness from Midea AI, validates PLC code through external compilation and live runtime execution, achieving...
Hugging Face Introduces SemComp-Bench to Test Whether Video Generators Actually Complete Tasks
A new benchmark from Hugging Face, SemComp-Bench, evaluates video generation models on semantic task completion, measuring both ou...
Co-RL: Multi-Agent RL Enables Unsupervised Reasoning Without Labels
Hugging Face researchers introduce Co-RL, a multi-agent reinforcement learning framework where models learn from peer-derived rewa...
Hugging Face Unveils Zetta: A Closed-Loop Harness for Self-Evolving Robots
Zetta, a new closed-loop embodied harness from Hugging Face, enables robots to evolve runtime critics and recovery skills online,...
HarnessRisk Benchmark Exposes Critical Configuration Flaws in AI Agent Safety
A new benchmark evaluates AI agent harness safety across six operational phases, finding that configuration vulnerabilities and de...
Energy-Guided Flow Matching: Coarse-to-Fine Generation with Moving Endpoints
A new method called Energy-Guided Flow Matching (EG-FM) improves image generation by explicitly modeling a coarse-to-fine trajecto...
SkillForge: Self-Distilling Agents Learn Project-Specific Skills Before Fixing Bugs
Hugging Face researchers introduce SkillForge, a self-distillation framework that synthesizes repository-specific issues to proact...
Hugging Face Researchers Propose Capability-Centric Data Design for Generalist Image Generation
A new paper from Hugging Face introduces a capability-driven data infrastructure with curriculum scheduling and specialized data e...