Eliahu Horwitz

Eliahu's activity

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

upvoted a paper about 2 months ago

DyPE: Dynamic Position Extrapolation for Ultra High Resolution Diffusion

Paper • 2510.20766 • Published Oct 23 • 34

upvoted a paper 3 months ago

Advancing Speech Understanding in Speech-Aware Language Models with GRPO

Paper • 2509.16990 • Published Sep 21 • 18

upvoted 2 papers 4 months ago

MV-RAG: Retrieval Augmented Multiview Diffusion

Paper • 2508.16577 • Published Aug 22 • 38

Story2Board: A Training-Free Approach for Expressive Storyboard Generation

Paper • 2508.09983 • Published Aug 13 • 68

upvoted 3 papers 6 months ago

Discrete Audio Tokens: More Than a Survey!

Paper • 2506.10274 • Published Jun 12 • 32

Auto-Regressive vs Flow-Matching: a Comparative Study of Modeling Paradigms for Text-to-Music Generation

Paper • 2506.08570 • Published Jun 10 • 33

Debatable Intelligence: Benchmarking LLM Judges via Debate Speech Evaluation

Paper • 2506.05062 • Published Jun 5 • 15

upvoted 4 papers 7 months ago

StressTest: Can YOUR Speech LM Handle the Stress?

Paper • 2505.22765 • Published May 28 • 17

CHIMERA: A Knowledge Base of Idea Recombination in Scientific Literature

Paper • 2505.20779 • Published May 27 • 15

Don't Overthink it. Preferring Shorter Thinking Chains for Improved LLM Reasoning

Paper • 2505.17813 • Published May 23 • 57

WHISTRESS: Enriching Transcriptions with Sentence Stress Detection

Paper • 2505.19103 • Published May 25 • 13

upvoted 3 papers 8 months ago

RefVNLI: Towards Scalable Evaluation of Subject-driven Text-to-image Generation

Paper • 2504.17502 • Published Apr 24 • 55

Scaling Analysis of Interleaved Speech-Text Language Models

Paper • 2504.02398 • Published Apr 3 • 31

Follow the Flow: On Information Flow Across Textual Tokens in Text-to-Image Models

Paper • 2504.01137 • Published Apr 1 • 21

upvoted 5 papers 9 months ago

OmnimatteZero: Training-free Real-time Omnimatte with Pre-trained Video Diffusion Models

Paper • 2503.18033 • Published Mar 23 • 27

Survey on Evaluation of LLM-based Agents

Paper • 2503.16416 • Published Mar 20 • 95

WildIFEval: Instruction Following in the Wild

Paper • 2503.06573 • Published Mar 9 • 14

Charting and Navigating Hugging Face's Model Atlas

Paper • 2503.10633 • Published Mar 13 • 92

RewardSDS: Aligning Score Distillation via Reward-Weighted Sampling

Paper • 2503.09601 • Published Mar 12 • 16

upvoted a collection 10 months ago

Slam

Collection

All resources for SpeechLMs from "Slamming: Training a Speech Language Model on One GPU in a Day". We provide tokeniser, lm, and datasets • 7 items • Updated May 22 • 13