From Table to Cell: Attention for Better Reasoning with TABALIGN
cs.AI
Submitted: 2026-05-14
Updated: 2026-10-03
Code: https://github.com/ThomasK1018/TabAlign
Terminology
Sources
- Qwen3-VL Technical Report
- Qwen2.5-VL Technical Report
- LLaDA2.0: Scaling Up Diffusion Language Models to 100B
- CQA-Eval: Designing Reliable Evaluations of Multi-paragraph Clinical QA under Resource Constraints
- The Llama 3 Herd of Models
- Enhancing Table Reasoning with Deterministic Table-State Rewards
- TABQAWORLD: Optimizing Multimodal Reasoning for Multi-Turn Table Question Answering
- Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization
- Ovis2.5 Technical Report
- Large Language Diffusion Models
- Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis
- Pre-Act: Multi-Step Planning and Reasoning Improves Acting in LLM Agents
- Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- HIPPO: Enhancing the Table Understanding Capability of LLMs through Hybrid-Modal Preference Optimization
- Qwen3 Technical Report
- DARE: Diffusion Large Language Models Alignment and Reinforcement Executor
- TableGPT-R1: Advancing Tabular Reasoning Through Reinforcement Learning
- ReAct: Synergizing Reasoning and Acting in Language Models
- Dream 7B: Diffusion Large Language Models
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems