Edward Williams

ZenithMap's activity

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

upvoted a paper 1 day ago

Learning to Steer, Steering to See: Unveiling the Geometry of RLVR in Large Language Models via Trainable Vectors

Paper • 2609.34344 • Published 14 days ago • 5

upvoted a paper 6 days ago

4DCodeBench: Benchmarking Agents on Inverse Graphics of Dynamic Scenes

Paper • 2610.03715 • Published 10 days ago • 34

upvoted a paper 22 days ago

When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation

Paper • 2609.20511 • Published 25 days ago • 115

upvoted a paper 23 days ago

What Does Privileged Information Add to On-Policy Self-Distillation?

Paper • 2609.20612 • Published 25 days ago • 36

upvoted a paper 29 days ago

X-AuT: Progressive Audio-Encoder Compression for Speech LLMs with Cross-Scale Distillation

Paper • 2609.11412 • Published Sep 10 • 48

upvoted a paper 30 days ago

Negative Self-Distillation: Learning to Reason by Avoiding Flaws

Paper • 2609.11699 • Published Sep 10 • 37

upvoted 4 papers about 1 month ago

Scaling Automatic Research Agents via World Models

Paper • 2608.12564 • Published Aug 29 • 489

Rethinking On-Policy Distillation of Large Language Models II: One Training Example

Paper • 2609.04172 • Published Sep 3 • 104

Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments

Paper • 2609.04148 • Published Sep 3 • 211

LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes

Paper • 2609.03796 • Published Sep 3 • 182

upvoted 7 papers about 2 months ago

Listening Forward: Next Patch Embedding Prediction Enables Scalable Audio Learners

Paper • 2608.19863 • Published Aug 20 • 6

SemComp-Bench: Benchmarking Semantic Task Completion in Video Generation

Paper • 2608.17426 • Published Aug 18 • 161

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 Aug 14 • 287

Self-Supervised Visual On-Policy Distillation

Paper • 2608.14144 • Published Aug 14 • 126

Alaya-EVOKE: From Linear-Scaling Supervision to Endless World

Paper • 2608.13546 • Published Aug 13 • 114

SkillZip: Contract-Preserving Graph Compression for Scalable Agent Skill Libraries

Paper • 2608.05604 • Published Aug 6 • 81

OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution

Paper • 2608.00677 • Published Aug 1 • 266

upvoted 3 papers 2 months ago

Agent Memory Distillation: Empowering Small LLM Agents with Hierarchical Teacher Memory

Paper • 2608.07169 • Published Aug 7 • 50

Invisible Shortcuts: Why Vision Encoders Know Your Camera

Paper • 2608.05424 • Published Aug 5 • 17

UniWorld-Design: From Pixel Generation to Layer-Native Design

Paper • 2608.03971 • Published Aug 4 • 25