Jue Hou

Marquis03's activity

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

updated a dataset about 21 hours ago

ProgramGym/programgym-1648

RL Environment • Updated about 21 hours ago • 1.65k • 1.72k • 3

New activity in ProgramGym/programgym-1648 1 day ago

Clarification on Context Resets and Switches in SFT Data Collection

1

#3 opened 1 day ago by

AdAstraAbyssoque

authored a paper 1 day ago

ProgramGym: Scaling Training Environments for Long-Horizon Program Reproduction Agents

Paper • 2610.13395 • Published 6 days ago • 54

liked a dataset 1 day ago

SinapisAI/RobustRouteBench

Viewer • Updated about 20 hours ago • 36.8k • 86 • 1

liked a model 1 day ago

AIGNLAI/RouteFM

Updated about 21 hours ago • 66 • 3

upvoted a collection 1 day ago

LLM Routing Research — Guannan Lai

Collection

Methods, supervision, benchmarks, evaluation tools, models, and demos for reliable and economical LLM routing. • 9 items • Updated 7 days ago • 2

liked a Space 1 day ago

Running

2

RouteFM Demo

🧭

2

Explore identity-free RouteFM routing across contexts.

liked a dataset 1 day ago

AIGNLAI/DARS

Viewer • Updated 4 days ago • 131k • 684 • 2

upvoted 6 papers 1 day ago

RouteJudge: An Open Platform for Reproducible and Preference-Aware LLM Routing

Paper • 2606.18774 • Published Jun 19 • 1

From Sampled Outcomes to Capability Distributions: Rethinking Supervision for LLM Routing

Paper • 2606.06924 • Published Jun 5 • 2

When Routing Collapses: On the Degenerate Convergence of LLM Routers

Paper • 2602.03478 • Published Feb 3 • 2

MMR-Bench: A Comprehensive Benchmark for Multimodal LLM Routing

Paper • 2601.17814 • Published Jan 25 • 1

Routing Should Pay for Itself: Sparse Supervision for Economical LLM Routing

Paper • 2609.37402 • Published 16 days ago • 19

Pretrain Once, Route Anywhere: Towards a Foundation Model for LLM Routing

Paper • 2609.37362 • Published 16 days ago • 19

upvoted a paper 3 days ago

ProgramGym: Scaling Training Environments for Long-Horizon Program Reproduction Agents

Paper • 2610.13395 • Published 6 days ago • 54

upvoted 2 papers 19 days ago

MM-R5: MultiModal Reasoning-Enhanced ReRanker via Reinforcement Learning for Document Retrieval

Paper • 2506.12364 • Published Jun 14, 2025 • 2

Reasoning-Enhanced Large Language Models for Molecular Property Prediction

Paper • 2510.10248 • Published Oct 11, 2025 • 3

upvoted a paper 3 months ago

MemSyco-Bench: Benchmarking Sycophancy in Agent Memory

Paper • 2607.01071 • Published Jul 1 • 27

upvoted a paper 8 months ago

TTCS: Test-Time Curriculum Synthesis for Self-Evolving

Paper • 2601.22628 • Published Jan 30 • 35

upvoted a paper 10 months ago

Improving Multi-step RAG with Hypergraph-based Memory for Long-Context Complex Relational Modeling

Paper • 2512.23959 • Published Dec 30, 2025 • 112