bingxuan li

bx6d's activity

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

upvoted a paper 4 days ago

Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning

Paper • 2609.03430 • Published 6 days ago • 170

upvoted a paper 7 days ago

StudentSim: Training LLM-based Student Simulators

Paper • 2609.01591 • Published 8 days ago • 484

updated a dataset 8 days ago

bx6d/r2s2r-data

Viewer • Updated 8 days ago • 265 • 174

published a dataset 21 days ago

bx6d/r2s2r-data

Viewer • Updated 8 days ago • 265 • 174

upvoted a paper 27 days ago

AI4AI at Test-Time: Strong-to-Weak Capability Transfer via Harnesses

Paper • 2608.12307 • Published 28 days ago • 115

upvoted 4 papers 2 months ago

Multi-Turn Agentic Scientific Literature Search via Workflow Induction

Paper • 2607.00597 • Published Jul 1 • 31

BioInsight: Multi-Agent Orchestration for Interactive Biomedical Knowledge Discovery

Paper • 2606.20997 • Published Jun 19 • 13

Trimming the Long-Tail of Visual World Modeling Evaluation

Paper • 2606.24256 • Published Jun 23 • 44

GBC: Gradient-Based Connections for Optimizing Multi-Agent Systems

Paper • 2606.28187 • Published Jun 26 • 14

submitted a paper to Daily Papers 2 months ago

Trimming the Long-Tail of Visual World Modeling Evaluation

Paper • 2606.24256 • Published Jun 23 • 44

updated a dataset 2 months ago

bx6d/tailor-bench

Updated Jun 26 • 39

published a dataset 2 months ago

bx6d/tailor-bench

Updated Jun 26 • 39

upvoted 3 papers 3 months ago

PlanBench-XL: Evaluating Long-Horizon Planning of LLM Tool-Use Agents in Large-Scale Tool Ecosystems

Paper • 2606.22388 • Published Jun 21 • 97

AdaPlanBench: Evaluating Adaptive Planning in Large Language Model Agents under World and User Constraints

Paper • 2606.05622 • Published Jun 4 • 45

Advancing Creative Physical Intelligence in Large Multimodal Models

Paper • 2605.26396 • Published May 25 • 22

upvoted 3 papers 4 months ago

Code as Agent Harness

Paper • 2605.18747 • Published May 18 • 227

Useful Memories Become Faulty When Continuously Updated by LLMs

Paper • 2605.12978 • Published May 13 • 20

CreativityBench: Evaluating Agent Creative Reasoning via Affordance-Based Tool Repurposing

Paper • 2605.02910 • Published May 6 • 24

upvoted a paper 5 months ago

PEARL: Self-Evolving Assistant for Time Management with Reinforcement Learning

Paper • 2601.11957 • Published Jan 28 • 3

updated a dataset 6 months ago

bx6d/EchoFoley-6k

Viewer • Updated Mar 26 • 8.62k • 27