TAP4LLM: Table Provider on Sampling, Augmenting, and Packing Semi-structured Data for Large Language Model Reasoning
Paper • 2312.09039 • Published
nbrl
non-profit
AI & ML interests
None defined yet.
Recent Activity
View all activity
zmoony
authored 19
papers about 2 months ago
MMTU: A Massive Multi-Task Table Understanding and Reasoning Benchmark
Paper • 2506.05587 • Published
Bingo: Boosting Efficient Reasoning of LLMs via Dynamic and Significance-based Reinforcement Learning
Paper • 2506.08125 • Published
GUI-360: A Comprehensive Dataset and Benchmark for Computer-Using Agents
Paper • 2511.04307 • Published • 17
Jupiter: Enhancing LLM Data Analysis Capabilities via Notebook and Inference-Time Value-Guided Search
Paper • 2509.09245 • Published
Fill the GAP: A Granular Alignment Paradigm for Visual Reasoning in Multimodal Large Language Models
Paper • 2605.12374 • Published
Grounding the Score: Explicit Visual Premise Verification for Reliable Vision-Language Process Reward Models
Paper • 2603.16253 • Published • 1
Rationale Matters: Learning Transferable Rubrics via Proxy-Guided Critique for VLM Reward Models
Paper • 2603.16600 • Published
MARCH: Multi-Agent Reinforced Self-Check for LLM Hallucination
Paper • 2603.24579 • Published • 1
Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
Paper • 2603.25158 • Published • 53
SheetBrain: A Neuro-Symbolic Agent for Accurate Reasoning over Complex and Large Spreadsheets
Paper • 2510.19247 • Published
ATP-Bench: Towards Agentic Tool Planning for MLLM Interleaved Generation
Paper • 2603.29902 • Published
Skill-RM: Unifying Heterogeneous Evaluation Criteria via Agent Skill
Paper • 2606.03980 • Published • 13
SiameseNorm: Breaking the Barrier to Reconciling Pre/Post-Norm
Paper • 2602.08064 • Published
Open Rubric System: Scaling Reinforcement Learning with Pairwise Adaptive Rubric
Paper • 2602.14069 • Published • 1
GD$^2$PO: Mitigating Multi-Reward Conflicts via Group-Dynamic reward-Decoupled Policy Optimization
Paper • 2606.16771 • Published • 12
Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills
Paper • 2607.22529 • Published • 44
SMOPD: Multi-Reward Reinforcement Learning via Specialize-and-Merge Online Policy Distillation
Paper • 2608.03092 • Published • 9
SpreadsheetLLM: Encoding Spreadsheets for Large Language Models
Paper • 2407.09025 • Published • 138
Paraloe1
published a
model 12 months ago