Research Papers
TraceDance Turns Real Agent Deployment Traces Into Targeted Behavior Benchmarks
Hugging Face paper TraceDance automatically builds benchmarks from real agent deployment traces to test specific undesirable behav...
YuE2 Unifies Symbolic and Audio Music Generation, Rivaling Suno
Hugging Face researchers introduce YuE2, a single Mixture-of-Transformers model that plans music as a readable score before render...
SLCA-GRPO Fixes Credit Misattribution in Tool-Calling RL
A new Hugging Face paper introduces SLCA-GRPO, a framework that locks credit assignment to structural segments so summary rewards...
TrackEverything Tracks Every Point in 3D Across 1000+ Frame Videos
A new 3D point tracker from Hugging Face researchers represents videos as persistent 3D scene tracks in world coordinates, breakin...
SAGE Framework Targets Long-Horizon Reasoning Biases in LLMs
A new paper introduces Symbolic Closure Analysis and the SAGE framework, which uses algebraic sparsification and hyperbolic struct...
D-JEPA Aligns Latent World Models With Real Execution Outcomes
A new latent world model, D-JEPA, learns decision-relevant relations among candidate futures from executed outcomes, improving act...
IndicBankBench Tests Whether Banking Assistants Are Reliably Safe, Not Just Plausible
A new 799-case benchmark for Indian retail banking evaluates language model assistants across four stages — safety, tool use, resp...
AgentWorld Benchmark Exposes Multi-Agent LLM Collaboration Gaps
Hugging Face researchers introduce AgentWorld, a 100-task benchmark for long-horizon multi-agent collaboration in an MMORPG sandbo...
Diffusion Model Refines Satellite 3D Maps, Cutting Elevation Error by Up to 43%
Researchers adapt Stable Diffusion 3 to refine noisy photogrammetric Digital Surface Models using Pléiades imagery, reducing RMSE...
Tactile-JEPA Brings Topology-Aware Self-Supervision to Robot Electronic Skins
A new self-supervised pre-training method for distributed tactile sensors predicts masked sensing elements using the sensor connec...
LastOPD Fixes Latent Distillation Collapse in Small Language Models
Hugging Face paper LastOPD identifies a collapse failure in latent on-policy distillation and proposes applying latent supervision...
TimeEvo Lets Time Series Agents Build Their Own Tool Libraries From Failure
A new Hugging Face paper argues that pre-supplied tool libraries misalign with agent needs and can silently degrade answers, propo...