HF Paper Explorer

Top AI research papers from the HuggingFace community

GitHub·HuggingFace Papers·Data © HuggingFace community

Last 3 Days

77 papers · page 1 of 2

AI Can Learn Scientific Taste

224

Mar 17, 2026Submitted by lkdhy

Mar 17, 2026

HuggingFace arXiv PDF

OpenSeeker: Democratizing Frontier Search Agents by Fully Open-Sourcing Training Data

131

Mar 17, 2026Submitted by yuwendu

Mar 17, 2026

HuggingFace arXiv PDF

EnterpriseOps-Gym: Environments and Evaluations for Stateful Agentic Planning and Tool Use in Enterprise Settings

131

Mar 17, 2026Submitted by BAJUKA

Mar 17, 2026

HuggingFace arXiv PDF

Grounding World Simulation Models in a Real-World Metropolis

114

Mar 17, 2026Submitted by

Mar 17, 2026

HuggingFace arXiv PDF

HSImul3R: Physics-in-the-Loop Reconstruction of Simulation-Ready Human-Scene Interactions

Mar 17, 2026Submitted by yukangcao

Mar 17, 2026

HuggingFace arXiv PDF

Attention Residuals

Mar 17, 2026Submitted by taesiri

Mar 17, 2026

HuggingFace arXiv PDF

LMEB: Long-horizon Memory Embedding Benchmark

Mar 16, 2026Submitted by Yuki131

Mar 16, 2026

HuggingFace arXiv PDF

Mixture-of-Depths Attention

Mar 17, 2026Submitted by LianghuiZhu

Mar 17, 2026

HuggingFace arXiv PDF

Can Vision-Language Models Solve the Shell Game?

Mar 16, 2026Submitted by

Mar 16, 2026

HuggingFace arXiv PDF

Cheers: Decoupling Patch Details from Semantic Representations Enables Unified Multimodal Comprehension and Generation

Mar 16, 2026Submitted by PengDa02

Mar 16, 2026

HuggingFace arXiv PDF

Effective Distillation to Hybrid xLSTM Architectures

Mar 17, 2026Submitted by sirluk

Mar 17, 2026

HuggingFace arXiv PDF

daVinci-Env: Open SWE Environment Synthesis at Scale

Mar 16, 2026Submitted by taesiri

Mar 16, 2026

HuggingFace arXiv PDF

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously

Mar 16, 2026Submitted by Catalan258

Mar 16, 2026

HuggingFace arXiv PDF

OmniForcing: Unleashing Real-time Joint Audio-Visual Generation

Mar 16, 2026Submitted by xzyhku

Mar 16, 2026

HuggingFace arXiv PDF

Anatomy of a Lie: A Multi-Stage Diagnostic Framework for Tracing Hallucinations in Vision-Language Models

Mar 17, 2026Submitted by LIQIIIII

Mar 17, 2026

HuggingFace arXiv PDF

Multimodal OCR: Parse Anything from Documents

Mar 16, 2026Submitted by akhaliq

Mar 16, 2026

HuggingFace arXiv PDF

ViFeEdit: A Video-Free Tuner of Your Video Diffusion Transformer

Mar 17, 2026Submitted by

Mar 17, 2026

HuggingFace arXiv PDF

POLCA: Stochastic Generative Optimization with LLM

Mar 17, 2026Submitted by allenanie

Mar 17, 2026

HuggingFace arXiv PDF

Visual-ERM: Reward Modeling for Visual Equivalence

Mar 16, 2026Submitted by taesiri

Mar 16, 2026

HuggingFace arXiv PDF

Safe and Scalable Web Agent Learning via Recreated Websites

Mar 17, 2026Submitted by hyungjoochae

Mar 17, 2026

HuggingFace arXiv PDF

MM-CondChain: A Programmatically Verified Benchmark for Visually Grounded Deep Compositional Reasoning

Mar 16, 2026Submitted by shilinyan

Mar 16, 2026

HuggingFace arXiv PDF

Make it SING: Analyzing Semantic Invariants in Classifiers

Mar 17, 2026Submitted by harel316

Mar 17, 2026

HuggingFace arXiv PDF

TERMINATOR: Learning Optimal Exit Points for Early Stopping in Chain-of-Thought Reasoning

Mar 17, 2026Submitted by

Mar 17, 2026

HuggingFace arXiv PDF

WebVR: Benchmarking Multimodal LLMs for WebPage Recreation from Videos via Human-Aligned Visual Rubrics

Mar 17, 2026Submitted by BroAlanTaps

Mar 17, 2026

HuggingFace arXiv PDF

V-Bridge: Bridging Video Generative Priors to Versatile Few-shot Image Restoration

Mar 16, 2026Submitted by desimfj

Mar 16, 2026

HuggingFace arXiv PDF

EvoScientist: Towards Multi-Agent Evolving AI Scientists for End-to-End Scientific Discovery

Mar 16, 2026Submitted by youganglyu

Mar 16, 2026

HuggingFace arXiv PDF

Understanding Reasoning in LLMs through Strategic Information Allocation under Uncertainty

Mar 17, 2026Submitted by beanie00

Mar 17, 2026

HuggingFace arXiv PDF

From Sparse to Dense: Multi-View GRPO for Flow Models via Augmented Condition Space

Mar 16, 2026Submitted by taesiri

Mar 16, 2026

HuggingFace arXiv PDF

HomeSafe-Bench: Evaluating Vision-Language Models on Unsafe Action Detection for Embodied Agents in Household Scenarios

Mar 16, 2026Submitted by

Mar 16, 2026

HuggingFace arXiv PDF

HybridStitch: Pixel and Timestep Level Model Stitching for Diffusion Acceleration

Mar 16, 2026Submitted by jt-zhang

Mar 16, 2026

HuggingFace arXiv PDF

Code-A1: Adversarial Evolving of Code LLM and Test LLM via Reinforcement Learning

Mar 17, 2026Submitted by taesiri

Mar 17, 2026

HuggingFace arXiv PDF

Panoramic Affordance Prediction

Mar 17, 2026Submitted by Chenfei-Liao

Mar 17, 2026

HuggingFace arXiv PDF

Riemannian Motion Generation: A Unified Framework for Human Motion Representation and Generation via Riemannian Flow Matching

Mar 17, 2026Submitted by Frank-miao

Mar 17, 2026

HuggingFace arXiv PDF

MMOU: A Massive Multi-Task Omni Understanding and Reasoning Benchmark for Long and Complex Real-World Videos

Mar 17, 2026Submitted by Sreyan88

Mar 17, 2026

HuggingFace arXiv PDF

Supervised Fine-Tuning versus Reinforcement Learning: A Study of Post-Training Methods for Large Language Models

Mar 17, 2026Submitted by FlippyDora

Mar 17, 2026

HuggingFace arXiv PDF

FineRMoE: Dimension Expansion for Finer-Grained Expert with Its Upcycling Approach

Mar 17, 2026Submitted by NingLiao

Mar 17, 2026

HuggingFace arXiv PDF

The PokeAgent Challenge: Competitive and Long-Context Learning at Scale

Mar 17, 2026Submitted by milkkarten

Mar 17, 2026

HuggingFace arXiv PDF

Learning Latent Proxies for Controllable Single-Image Relighting

Mar 17, 2026Submitted by Zanghu-Ze

Mar 17, 2026

HuggingFace arXiv PDF

Training-free Detection of Generated Videos via Spatial-Temporal Likelihoods

Mar 17, 2026Submitted by Yossilevii100

Mar 17, 2026

HuggingFace arXiv PDF

RS-WorldModel: a Unified Model for Remote Sensing Understanding and Future Sense Forecasting

Mar 17, 2026Submitted by Czi24

Mar 17, 2026

HuggingFace arXiv PDF

Motivation in Large Language Models

Mar 17, 2026Submitted by omer6nahum

Mar 17, 2026

HuggingFace arXiv PDF

VQQA: An Agentic Approach for Video Evaluation and Quality Improvement

Mar 16, 2026Submitted by taesiri

Mar 16, 2026

HuggingFace arXiv PDF

Think While Watching: Online Streaming Segment-Level Memory for Multi-Turn Video Reasoning in Multimodal Large Language Models

Mar 16, 2026Submitted by wanglu666

Mar 16, 2026

HuggingFace arXiv PDF

Spend Less, Reason Better: Budget-Aware Value Tree Search for LLM Agents

Mar 16, 2026Submitted by taesiri

Mar 16, 2026

HuggingFace arXiv PDF

LookaheadKV: Fast and Accurate KV Cache Eviction by Glimpsing into the Future without Generation

Mar 16, 2026Submitted by ingyu

Mar 16, 2026

HuggingFace arXiv PDF

Taking Shortcuts for Categorical VQA Using Super Neurons

Mar 16, 2026Submitted by pmusacchio

Mar 16, 2026

HuggingFace arXiv PDF

VisionCoach: Reinforcing Grounded Video Reasoning via Visual-Perception Prompting

Mar 17, 2026Submitted by Shoubin

Mar 17, 2026

HuggingFace arXiv PDF

Steve-Evolving: Open-World Embodied Self-Evolution via Fine-Grained Diagnosis and Dual-Track Knowledge Distillation

Mar 16, 2026Submitted by Zhisheng888

Mar 16, 2026

HuggingFace arXiv PDF

NanoVDR: Distilling a 2B Vision-Language Retriever into a 70M Text-Only Encoder for Visual Document Retrieval

Mar 16, 2026Submitted by Ryenhails

Mar 16, 2026

HuggingFace arXiv PDF

CreativeBench: Benchmarking and Enhancing Machine Creativity via Self-Evolving Challenges

Mar 16, 2026Submitted by zzzzhw

Mar 16, 2026

HuggingFace arXiv PDF

1 / 2