Sea Language Team

sail-lm's activity

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

tcftrees 

authored 2 papers 3 days ago

LEGO-RL: Harness-Native Reinforcement Learning for Coding Agents

Paper • 2608.17393 • Published Aug 18 • 27

SWE-Review: Closing the Loop on Issue Resolution with Agentic Code Review

Paper • 2607.06065 • Published Jul 7 • 11

Xalphinions 

submitted a paper to Daily Papers 3 days ago

ProVe: Proposer-Verifier Decoding

Paper • 2610.27815 • Published 17 days ago • 8

dreamerdeo 

authored a paper 3 months ago

UI-Mate: Advancing Open-Weight Foundation GUI Agents with In-Context Demonstrations

Paper • 2608.15930 • Published Aug 16 • 48

tcftrees 

authored a paper 4 months ago

Prefilling-dLLM: Predictive Prefilling for Long-Context Inference in Diffusion Language Models

Paper • 2606.10537 • Published Jun 9

tcftrees 

authored 6 papers 5 months ago

MMFormalizer: Multimodal Autoformalization in the Wild

Paper • 2601.03017 • Published Jan 6 • 38

MMDeepResearch-Bench: A Benchmark for Multimodal Deep Research Agents

Paper • 2601.12346 • Published Jan 18 • 52

OVD: On-policy Verbal Distillation

Paper • 2601.21968 • Published Jan 29 • 6

From Verifiable Dot to Reward Chain: Harnessing Verifiable Reference-based Rewards for Reinforcement Learning of Open-ended Generation

Paper • 2601.18533 • Published Jan 26

GRPO-VPS: Enhancing Group Relative Policy Optimization with Verifiable Process Supervision for Effective Reasoning

Paper • 2604.20659 • Published Apr 22 • 1

What Makes Interaction Trajectories Effective for Training Terminal Agents?

Paper • 2606.03461 • Published Jun 2 • 4

Xalphinions 

authored 4 papers 7 months ago

Self-Rewarding Sequential Monte Carlo for Masked Diffusion Language Models

Paper • 2602.01849 • Published Feb 2 • 5

Document Reconstruction Unlocks Scalable Long-Context RLVR

Paper • 2602.08237 • Published Feb 9

MiroEval: Benchmarking Multimodal Deep Research Agents in Process and Outcome

Paper • 2603.28407 • Published Mar 30 • 70

MARS: Enabling Autoregressive Models Multi-Token Generation

Paper • 2604.07023 • Published Apr 8 • 37

Xalphinions 

submitted a paper to Daily Papers 7 months ago

MARS: Enabling Autoregressive Models Multi-Token Generation

Paper • 2604.07023 • Published Apr 8 • 37

tcftrees 

authored a paper 10 months ago

SWE-Lego: Pushing the Limits of Supervised Fine-tuning for Software Issue Resolving

Paper • 2601.01426 • Published Jan 4 • 25

Xalphinions 

submitted a paper to Daily Papers 10 months ago

On the Role of Discreteness in Diffusion LLMs

Paper • 2512.22630 • Published Dec 27, 2025 • 18

tcftrees 

authored 2 papers 12 months ago

LongEmotion: Measuring Emotional Intelligence of Large Language Models in Long-Context Interaction

Paper • 2509.07403 • Published Sep 9, 2025 • 31

Electrocardiogram Instruction Tuning for Report Generation

Paper • 2403.04945 • Published Mar 7, 2024 • 2