董若曦's picture

9 5

董若曦

JacksonWhite66

AI & ML interests

None yet

Recent Activity

upvoted a paper 5 days ago

FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents

upvoted a paper 5 days ago

InterleaveThinker: Reinforcing Agentic Interleaved Generation

upvoted a paper 5 days ago

ABot-Earth 0.5: Generative 3D Earth Model

View all activity

Organizations

None yet

upvoted 4 papers 5 days ago

FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents

Paper • 2606.12087 • Published 7 days ago • 72

InterleaveThinker: Reinforcing Agentic Interleaved Generation

Paper • 2606.13679 • Published 6 days ago • 78

ABot-Earth 0.5: Generative 3D Earth Model

Paper • 2606.09967 • Published 9 days ago • 468

Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks

Paper • 2606.12344 • Published 7 days ago • 65

upvoted a paper 7 days ago

Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory Rollouts

Paper • 2606.05922 • Published 13 days ago • 52

upvoted a paper 8 days ago

Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models

Paper • 2606.03988 • Published 14 days ago • 119

upvoted 2 papers 13 days ago

On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters

Paper • 2606.02437 • Published 16 days ago • 228

Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding

Paper • 2605.29707 • Published 20 days ago • 145

upvoted a paper 19 days ago

Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players

Paper • 2605.28816 • Published 21 days ago • 423