leo

duckking032's activity

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

upvoted a paper 1 day ago

Science or Slop?: Benchmarking and Mitigating Scientific Slop in AI-Generated Papers

Paper • 2610.00531 • Published 11 days ago • 62

upvoted 2 papers 10 days ago

VisionHOPE: Visual Backbones as Self-Modifying Learning Systems

Paper • 2609.33325 • Published 14 days ago • 342

The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation

Paper • 2609.36484 • Published 12 days ago • 553

upvoted a paper 15 days ago

Compile by Training: Turning Natural-Language Specifications into Local Neural Functions

Paper • 2609.04199 • Published Sep 3 • 332

upvoted 3 papers 16 days ago

Why Do Video Diffusion Models Violate Physics? Unveiling the Flaws in Attention Mechanisms

Paper • 2609.23658 • Published 21 days ago • 30

Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs

Paper • 2609.29845 • Published 17 days ago • 105

Training Object Permanence in World Models

Paper • 2609.28654 • Published 18 days ago • 181

upvoted a paper 19 days ago

RRSI: Regularized Recursive Self-Improvement of Agent Harnesses

Paper • 2609.24972 • Published 20 days ago • 225

upvoted a paper 23 days ago

DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression

Paper • 2609.19969 • Published 24 days ago • 228

upvoted 10 papers about 1 month ago

Φ-Bench: Can Large Language Models Engineer the Infrastructure That Powers Them?

Paper • 2609.10226 • Published Sep 9 • 19

NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness

Paper • 2609.08183 • Published Sep 8 • 321

Unlocking Lossless Speedups in LLMs via Discrete Diffusion

Paper • 2609.04010 • Published Sep 3 • 114

Don't Drop Dropout: Optimizing Layer Sparsity for Efficient LLM Training and Inference

Paper • 2609.05275 • Published Sep 4 • 26

MaxKernel: Agentic Kernel Generation for TPUs

Paper • 2609.04523 • Published Sep 3 • 20

Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments

Paper • 2609.04148 • Published Sep 3 • 211

SMELT: Scaling Laws for Compute-Matched MoE Looped Transformers

Paper • 2609.01343 • Published Sep 1 • 92

On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability

Paper • 2608.30320 • Published Aug 31 • 63

DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation

Paper • 2607.05147 • Published Jul 6 • 51

Don't Retrain, Align: Adapting Autoregressive LMs to Diffusion LMs via Representation Alignment

Paper • 2605.06885 • Published May 7 • 1

upvoted a paper about 2 months ago

Prime Agent: A Self-Improving RLM Harness

Paper • 2608.23552 • Published Aug 24 • 58