HuggingFace
OmniOpt: Taxonomy, Geometry, and Benchmarking of Modern Optimizers
Optimizer selection for large-scale model training has become a system-level design decision constrained jointly by c...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
Do All Visual Tokens Matter Equally? Object-Evidence Preserving Token Merging for Vision-Language Retrieval
Multi-vector vision-language retrieval preserves fine-grained visual evidence through maximum-similarity late interac...
HuggingFace
Perceptual Flow Matching for Few-Step Generative Modeling
We propose Perceptual Flow Matching (PFM), a simple yet effective framework for few-step generation in flow-matching ...
HuggingFace
CONFLUX: A Latent Diusion Model for 3D Chest-CT Synthesis with RL Post-Training
Controllable generative models of 3D medical images can synthesize volumes with specified clinical attributes, but th...
HuggingFace
MV-Forcing: Long Multi-View Video Generation via 4D-Grounded Spatio-Temporal Self-Forcing
Recent advances in video diffusion models have enabled either long single-view generation through temporal autoregres...
HuggingFace
KVpop -- Key-Value Cache Compression with Predictive Online Pruning
Key-value (KV) cache growth is a major bottleneck in autoregressive decoding, as memory and bandwidth scale linearly ...
HuggingFace
Multi-Turn Agentic Scientific Literature Search via Workflow Induction
Scientific literature search often requires more than retrieving papers from a single query: users' intents are under...
HuggingFace
AnyBokeh: Physics-Guided Any-to-Any Bokeh Editing with Optical Fingerprint Transfer
Depth-of-field control is a fundamental tool in photography, yet post-capture bokeh editing from a single image remai...
HuggingFace
Generated Contents Enrichment
We study Generated Contents Enrichment (GCE), a conditional image-generation task in which a sparse scene description...
HuggingFace
Measuring the Gap Between Human and LLM Research Ideas
LLMs are increasingly used to brainstorm research ideas, but existing evaluations mostly judge individual ideas by no...
HuggingFace
Teaching LLMs to Recommend and Defer in Underrepresented Epilepsy Care
Specialist epilepsy expertise is scarce in resource-constrained settings, making LLM-based decision support attractiv...
HuggingFace
Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous Robots
Embodied AI models now span vision-language-action (VLA) models and world-action models (WAMs), but practical deploym...