FSMBench

FSMBench's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Articles

taesiri 

submitted a paper to Daily Papers about 16 hours ago

SeeUPO: Sequence-Level Agentic-RL with Convergence Guarantees

Paper • 2602.06554 • Published 3 days ago • 2

taesiri 

submitted 4 papers to Daily Papers about 18 hours ago

EgoAVU: Egocentric Audio-Visual Understanding

Paper • 2602.06139 • Published 4 days ago • 9

DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos

Paper • 2602.06949 • Published 3 days ago • 20

POINTS-GUI-G: GUI-Grounding Journey

Paper • 2602.06391 • Published 4 days ago • 14

InftyThink+: Effective and Efficient Infinite-Horizon Reasoning via Reinforcement Learning

Paper • 2602.06960 • Published 3 days ago • 6

taesiri 

submitted 5 papers to Daily Papers 4 days ago

Late-to-Early Training: LET LLMs Learn Earlier, So Faster and Better

Paper • 2602.05393 • Published 5 days ago • 6

ProAct: Agentic Lookahead in Interactive Environments

Paper • 2602.05327 • Published 5 days ago • 23

BABE: Biology Arena BEnchmark

Paper • 2602.05857 • Published 4 days ago • 10

Pathwise Test-Time Correction for Autoregressive Long Video Generation

Paper • 2602.05871 • Published 4 days ago • 3

FastVMT: Eliminating Redundancy in Video Motion Transfer

Paper • 2602.05551 • Published 4 days ago • 3

taesiri 

submitted 5 papers to Daily Papers 5 days ago

Likelihood-Based Reward Designs for General LLM Reasoning

Paper • 2602.03979 • Published 6 days ago • 8

ERNIE 5.0 Technical Report

Paper • 2602.04705 • Published 5 days ago • 242

Skin Tokens: A Learned Compact Representation for Unified Autoregressive Rigging

Paper • 2602.04805 • Published 5 days ago • 5

HY3D-Bench: Generation of 3D Assets

Paper • 2602.03907 • Published 6 days ago • 22

Protein Autoregressive Modeling via Multiscale Structure Generation

Paper • 2602.04883 • Published 5 days ago • 3

taesiri 

submitted 5 papers to Daily Papers 6 days ago

CoBA-RL: Capability-Oriented Budget Allocation for Reinforcement Learning in LLMs

Paper • 2602.03048 • Published 7 days ago • 33

MARS: Modular Agent with Reflective Search for Automated AI Research

Paper • 2602.02660 • Published 7 days ago • 58

Search-R2: Enhancing Search-Integrated Reasoning via Actor-Refiner Collaboration

Paper • 2602.03647 • Published 6 days ago • 7

WorldVQA: Measuring Atomic World Knowledge in Multimodal Large Language Models

Paper • 2602.02537 • Published 12 days ago • 5

Accelerating Scientific Research with Gemini: Case Studies and Common Techniques

Paper • 2602.03837 • Published 6 days ago • 4