Levi Lewis

levilewis's activity

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

upvoted a paper 20 days ago

Quantifying and Expanding the Theoretical Capacity of Late-Interaction Retrieval Models

Paper • 2607.05803 • Published 24 days ago • 10

upvoted 2 papers 25 days ago

The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning

Paper • 2606.29526 • Published Jun 28 • 170

Bridging VideoQA and Video-Guided Agentic Tasks via Generalized Keyframe Extraction

Paper • 2606.29445 • Published Jun 28 • 28

upvoted a paper 28 days ago

Cognitive Episodes in LLM Reasoning Traces Enable Interpretable Human Item Difficulty Prediction

Paper • 2606.28186 • Published Jun 26 • 9

upvoted 2 papers about 2 months ago

A Multi-AI-agent Framework Enabling End-to-end Finite Element Analysis for Solid Mechanics Problems

Paper • 2606.00138 • Published May 28 • 6

Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs

Paper • 2605.30611 • Published May 28 • 253

upvoted 5 papers 2 months ago

Cross-scale Aligned Supervision for Training GANs

Paper • 2605.26449 • Published May 26 • 3

Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players

Paper • 2605.28816 • Published May 27 • 433

MotiMotion: Motion-Controlled Video Generation with Visual Reasoning

Paper • 2605.22818 • Published May 21 • 5

A Survey of Large Audio Language Models: Generalization, Trustworthiness, and Outlook

Paper • 2605.20266 • Published May 18 • 56

From Plans to Pixels: Learning to Plan and Orchestrate for Open-Ended Image Editing

Paper • 2605.15181 • Published May 14 • 12

upvoted 5 papers 3 months ago

The Scaling Properties of Implicit Deductive Reasoning in Transformers

Paper • 2605.04330 • Published May 5 • 5

End-to-End Autoregressive Image Generation with 1D Semantic Tokenizer

Paper • 2605.00503 • Published May 1 • 13

From Context to Skills: Can Language Models Learn from Context Skillfully?

Paper • 2604.27660 • Published May 3 • 171

Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond

Paper • 2604.22748 • Published Apr 24 • 232

Recursive Multi-Agent Systems

Paper • 2604.25917 • Published Apr 28 • 287

upvoted 4 papers 4 months ago

A Systematic Study of Cross-Modal Typographic Attacks on Audio-Visual Reasoning

Paper • 2604.03995 • Published Apr 5 • 4

MARS: Enabling Autoregressive Models Multi-Token Generation

Paper • 2604.07023 • Published Apr 8 • 38

HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents

Paper • 2604.07430 • Published Apr 8 • 181

CUE-R: Beyond the Final Answer in Retrieval-Augmented Generation

Paper • 2604.05467 • Published Apr 7 • 7