HuggingFace
Three-Body Scattering for Generative Modeling
Modern generative models typically rely on an adversarial critic, a prescribed noise-to-data path, or an autoregressi...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
Spectral Prior for Reducing Exposure Bias in Diffusion Models
Diffusion models typically suffer from error accumulation during iterative sampling, commonly referred to as exposure...
HuggingFace
Multimodal Speaker Verification as a Threat to Speaker Anonymization
Most automatic speaker verification (ASV) systems operate on individual utterances, despite real-world interactions t...
HuggingFace
Self-Supervised Learning of Structured Dynamics from Videos
Understanding motion in video is a fundamental challenge for visual learning, as frame-to-frame change entangles two ...
HuggingFace
FinanceComplexQA: Benchmarking Agentic Reasoning on Industrial-grade Financial Documents
Agentic Reasoning has become a transformative force in financial analysis due to its ability to integrate large-scale...
HuggingFace
SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation
We introduce SANA-Video 2.0, a hybrid video diffusion transformer instantiated at 5B and 14B scales under a unified a...
HuggingFace
Multi-Turn On-Policy Distillation with Prefix Replay
We study on-policy distillation (OPD) for agentic tasks, where an LLM agent interacts with an environment over multip...
HuggingFace
Dataset Distillation by Influence Matching
We revisit dataset distillation from an outcome-centric perspective. Rather than aligning process surrogates (per-ste...
HuggingFace
OpenForgeRL: Train Harness-native Agents in Any Environment
Modern AI agents rely on elaborate inference harnesses such as Claude Code, Codex, and OpenClaw to drive multi-turn r...
arXiv
Same Dangerous Objective, Opposite Advice: Direct Exposure versus Multi-Agent Mediation
Even a current high-capability LLM can appear safer when shown a dangerous objective directly than when other agents ...
arXiv
GS-Agent: Creating 4D Physical Worlds With Generative Simulation
Creating dynamic and physically realistic 4D worlds from natural language descriptions is both fascinating and challe...
arXiv
ElasticTTT: Prior-Preserving Test-Time Tuning for Video Editing
Test-Time Tuning (TTT) on pretrained diffusion models has emerged as a powerful paradigm for video editing. However, ...