Zhen Fang

CostaliyA's activity

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

upvoted a paper 10 days ago

Super Star: Towards Streaming Real-time Interactive Agents for Digital Humans

Paper • 2608.24909 • Published Jul 22 • 6

upvoted a paper 18 days ago

FACET: Preserving Source Intent and Executable State in Terminal Task Synthesis

Paper • 2608.18580 • Published 19 days ago • 121

upvoted a paper 24 days ago

AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design

Paper • 2608.13560 • Published 25 days ago • 56

upvoted a paper 26 days ago

SPIEval: Evaluating Large Language Models as Mobile Assistants over Scattered Personal Information

Paper • 2608.10692 • Published 27 days ago • 12

upvoted 3 papers 27 days ago

Evo-Bench: Can Language Models Improve Agent Harness?

Paper • 2608.09096 • Published 28 days ago • 18

Beyond Simply Environment Scaling: Designing Effective Environment Distributions for Multimodal Agent Learning

Paper • 2608.03571 • Published Aug 6 • 46

SPOT: Sparse Probing and Outcome Calibration for On-Policy Distillation

Paper • 2608.04419 • Published Aug 5 • 28

upvoted 2 papers 28 days ago

AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning

Paper • 2608.05987 • Published Aug 6 • 101

Reinforcement Learning with Evolving Rubrics as Rewards for Audio Reasoning

Paper • 2608.02831 • Published Aug 3 • 15

upvoted 5 papers about 1 month ago

Any-OPD: Heterogeneous On-Policy Distillation for Flow-Matching Models via Representation-Space Bridging

Paper • 2608.03316 • Published Aug 4 • 26

Video-DeepResearch: Towards the Next-Generation Multimodal Deepresearch Agent

Paper • 2608.03979 • Published Aug 4 • 53

LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks

Paper • 2608.01964 • Published Aug 3 • 183

VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System

Paper • 2607.27380 • Published Jul 29 • 72

Kimi K3: Open Frontier Intelligence

Paper • 2607.24653 • Published Jul 27 • 514

upvoted an article about 1 month ago

view article

Article

Kimi K3 Model Overview: 2.8T Parameters, MXFP4 Quantization, and What the Open Weights Mean for the Community

• 

ResterChed

•

Jul 17

• 197

upvoted 4 papers about 2 months ago

Self Gradient Forcing: Native Long Video Extrapolation

Paper • 2607.20368 • Published Jul 22 • 36

TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs

Paper • 2607.17423 • Published Jul 19 • 167

SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning

Paper • 2607.14777 • Published Jul 16 • 107

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding

Paper • 2607.14935 • Published Jul 16 • 172

upvoted a paper 2 months ago

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence

Paper • 2607.07675 • Published Jul 8 • 64