Starstrek

Stars321123's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 5 papers about 2 hours ago

From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents

Paper • 2603.22386 • Published 2 days ago • 34

SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and Planning

Paper • 2603.23483 • Published about 20 hours ago • 35

SIMART: Decomposing Monolithic Meshes into Sim-ready Articulated Assets via MLLM

Paper • 2603.23386 • Published about 21 hours ago • 30

MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding

Paper • 2603.22458 • Published 2 days ago • 104

ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model

Paper • 2603.22281 • Published 2 days ago • 8

upvoted a paper about 5 hours ago

UniGRPO: Unified Policy Optimization for Reasoning-Driven Visual Generation

Paper • 2603.23500 • Published about 20 hours ago • 25

upvoted a changelog about 18 hours ago

view changelog

Hugging Face Changelog

Introducing hf-mount

about 24 hours ago

• 83

upvoted a paper about 19 hours ago

VideoDetective: Clue Hunting via both Extrinsic Query and Intrinsic Relevance for Long Video Understanding

Paper • 2603.22285 • Published 2 days ago • 45

upvoted 2 papers 1 day ago

VTC-Bench: Evaluating Agentic Multimodal Models via Compositional Visual Tool Chaining

Paper • 2603.15030 • Published 9 days ago • 19

Alignment Makes Language Models Normative, Not Descriptive

Paper • 2603.17218 • Published 8 days ago • 46

upvoted 2 articles 1 day ago

view article

Article

**LoRA Fine-Tuning BitNet b1.58 LLMs on Heterogeneous Edge GPUs via QVAC Fabric**

• 

8 days ago

•

14

view article

Article

A New Framework for Evaluating Voice Agents (EVA)

• 

1 day ago

•

70

upvoted 6 papers 1 day ago

MonoArt: Progressive Structural Reasoning for Monocular Articulated 3D Reconstruction

Paper • 2603.19231 • Published 6 days ago • 36

SegviGen: Repurposing 3D Generative Model for Part Segmentation

Paper • 2603.16869 • Published 8 days ago • 18

V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning

Paper • 2603.14482 • Published 10 days ago • 21

Speed by Simplicity: A Single-Stream Architecture for Fast Audio-Video Generative Foundation Model

Paper • 2603.21986 • Published 2 days ago • 97

LongCat-Flash-Prover: Advancing Native Formal Reasoning via Agentic Tool-Integrated Reinforcement Learning

Paper • 2603.21065 • Published 3 days ago • 64

FinToolBench: Evaluating LLM Agents for Real-World Financial Tool Use

Paper • 2603.08262 • Published 16 days ago • 43

upvoted a collection 1 day ago

Llama-Embed-Nemotron-8B

Collection

State-of-the-Art Text Embedding Model • 3 items • Updated about 16 hours ago • 5

upvoted an article 1 day ago

view article

Article

SynthVision: Building a 110K Synthetic Medical VQA Dataset with Cross-Model Validation

• 

2 days ago

•

11