Eli Wren

eliwren's activity

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

upvoted a paper 1 day ago

Zetta ζ: An Efficient Closed-Loop Embodied Harness for Self-Evolving Physical Intelligence

Paper • 2608.16590 • Published 8 days ago • 145

upvoted a paper 2 days ago

ASI-Bench: At the Dawn of Artificial Superintelligence

Paper • 2608.17271 • Published 7 days ago • 61

upvoted 5 papers 3 days ago

Are You Sure You're Sure? On the Impact of Instruction Tuning on Confidence and Lexical Diversity

Paper • 2608.13430 • Published 12 days ago • 13

Cross-Model Memory Transfer via Target-Side Reader Adaptation

Paper • 2608.17050 • Published 8 days ago • 6

VideoGAIA: A Benchmark for General AI Assistants on Agentic Video Understanding

Paper • 2608.14718 • Published 13 days ago • 10

ENTLORE: A Graph-Grounded Benchmark for Latent Organizational Reasoning in Enterprise Question Answering

Paper • 2608.10679 • Published 14 days ago • 6

Demystifying Agent Skills: Why They Work-Until They Don't

Paper • 2608.14036 • Published 11 days ago • 163

upvoted 2 papers 4 days ago

Dynamic Multi-Byte Prediction With Hierarchical Language Models

Paper • 2608.15454 • Published 9 days ago • 19

Harness the Memory: A Holistic Evaluation of Memory Substrates in Memory Agents

Paper • 2608.15008 • Published 10 days ago • 15

upvoted a paper 5 days ago

Can We Defend Against AI-Generated Video Attacks on Real-World Crisis Events? A Systematic Evaluation of Detectors, Generators and Social Dissemination

Paper • 2608.14391 • Published 11 days ago • 277

upvoted a paper 6 days ago

A Pathway to General-Purpose Scientific AI: Multimodal Comprehension of Scientific Images

Paper • 2608.14075 • Published 11 days ago • 4

upvoted a paper 8 days ago

Simplex Relaxation for Discrete Diffusion

Paper • 2608.10615 • Published 14 days ago • 6

upvoted a paper 9 days ago

Beyond Pixels: From Video Priors to 4D Worlds

Paper • 2608.10744 • Published 14 days ago • 182

upvoted 2 papers 10 days ago

Relevant but Incomplete: Referential Dangling as a Paradigm-Level Failure Mode in Hard Prompt Compression

Paper • 2608.04569 • Published 20 days ago • 13

SkillZip: Evaluation-Free Skill Compression for Self-Evolving Agents by Discovering Reusable Structure

Paper • 2608.11079 • Published 14 days ago • 17

upvoted 2 papers 11 days ago

CoinRAG: Contextualized Information Nugget KV Cache Reuse for Long-Context RAG

Paper • 2608.07458 • Published 18 days ago • 10

AdvFD: Boosting Visual Generation via Adversarial Fr'echet Distance Loss

Paper • 2608.11205 • Published 14 days ago • 27

upvoted a paper 12 days ago

BDH-CQ: In-Context Learning with Recurrent Latent Reasoning

Paper • 2608.09888 • Published 15 days ago • 752

upvoted a paper 13 days ago

EnvACE: Internalizing Environment Dynamics via World Rehearsal for Agentic Reinforcement Learning

Paper • 2608.06197 • Published 19 days ago • 46

upvoted a paper 14 days ago

MameLoshnLM: Yiddish Language Model and Evaluation Benchmark

Paper • 2608.05850 • Published 19 days ago • 23