Thomas Katraouras

Tomk187's activity

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

upvoted 2 papers 1 day ago

Language of Thought Shapes Output Diversity in Large Language Models

Paper • 2601.11227 • Published 4 days ago • 1

AstroReason-Bench: Evaluating Unified Agentic Planning across Heterogeneous Space Planning Problems

Paper • 2601.11354 • Published 4 days ago • 2

upvoted 18 papers 2 days ago

VERSE: Visual Embedding Reduction and Space Exploration. Clustering-Guided Insights for Training Data Enhancement in Visually-Rich Document Understanding

Paper • 2601.05125 • Published 12 days ago • 1

RelayLLM: Efficient Reasoning via Collaborative Decoding

Paper • 2601.05167 • Published 12 days ago • 28

RL-AWB: Deep Reinforcement Learning for Auto White Balance Correction in Low-Light Night-time Scenes

Paper • 2601.05249 • Published 12 days ago • 45

Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency

Paper • 2601.05905 • Published 11 days ago • 18

DrivingGen: A Comprehensive Benchmark for Generative Video World Models in Autonomous Driving

Paper • 2601.01528 • Published 16 days ago • 18

GlimpRouter: Efficient Collaborative Inference by Glimpsing One Token of Thoughts

Paper • 2601.05110 • Published 12 days ago • 27

A^3-Bench: Benchmarking Memory-Driven Scientific Reasoning via Anchor and Attractor Activation

Paper • 2601.09274 • Published 7 days ago • 80

Toward Ultra-Long-Horizon Agentic Science: Cognitive Accumulation for Machine Learning Engineering

Paper • 2601.10402 • Published 5 days ago • 35

EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis

Paper • 2601.05808 • Published 11 days ago • 35

MemoBrain: Executive Memory as an Agentic Brain for Reasoning

Paper • 2601.08079 • Published 8 days ago • 36

MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head

Paper • 2601.07832 • Published 8 days ago • 46

KnowMe-Bench: Benchmarking Person Understanding for Lifelong Digital Companions

Paper • 2601.04745 • Published 12 days ago • 55

Distribution-Aligned Sequence Distillation for Superior Long-CoT Reasoning

Paper • 2601.09088 • Published 7 days ago • 54

MAXS: Meta-Adaptive Exploration with LLM Agents

Paper • 2601.09259 • Published 7 days ago • 91

RealMem: Benchmarking LLMs in Real-World Memory-Driven Interaction

Paper • 2601.06966 • Published 9 days ago • 7

The Agent's First Day: Benchmarking Learning, Exploration, and Scheduling in the Workplace Scenarios

Paper • 2601.08173 • Published 8 days ago • 7

Beyond Hard Masks: Progressive Token Evolution for Diffusion Language Models

Paper • 2601.07351 • Published 8 days ago • 24

Think-Then-Generate: Reasoning-Aware Text-to-Image Diffusion with LLM Encoders

Paper • 2601.10332 • Published 5 days ago • 27