PixRestore: Unified Image Restoration via Pixel Diffusion Transformer
Paper • 2608.16793 • Published • 1
Kye Gomez
kye
AI & ML interests
Neuroscience, Behavior Science, Anti-Matter, Anti-Gravity propulsion,
Recent Activity
upvoted a paper about 7 hours ago
PixRestore: Unified Image Restoration via Pixel Diffusion Transformer upvoted a paper about 7 hours ago
MoE-ViE: Mixture of Experts Vision Encoder for Efficient Image and Video Understanding upvoted a paper about 7 hours ago
Dynamic Multi-Byte Prediction With Hierarchical Language ModelsOrganizations
upvoted 7
papers about 7 hours ago
MoE-ViE: Mixture of Experts Vision Encoder for Efficient Image and Video Understanding
Paper • 2608.17402 • Published • 9
Dynamic Multi-Byte Prediction With Hierarchical Language Models
Paper • 2608.15454 • Published • 12
Energy-Guided Flow Matching
Paper • 2608.05811 • Published • 8
V-RAE: Rethinking Video Latent Spaces for Generation
Paper • 2608.13556 • Published • 15
FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution
Paper • 2608.16157 • Published • 43
ASI-Bench: At the Dawn of Artificial Superintelligence
Paper • 2608.17271 • Published • 51
upvoted 4
papers 1 day ago
HarnessEval-W: Agentifying the Evaluation of Visual Worlds
Paper • 2608.16859 • Published • 116
Improving the matrix multiplication exponent with modern optimization and AlphaEvolve
Paper • 2608.16884 • Published • 14
Understanding Cognition-Induced Risks in Agentic AI Systems
Paper • 2608.15304 • Published • 16
MOSS-VL Technical Report
Paper • 2608.15045 • Published • 42
upvoted 4
papers 2 days ago
Multimodal Model Diffing for Feature Discovery and Control
Paper • 2608.09928 • Published • 9
Second Thought: Reasoning in Parallel as LLM Agents Act and Observe
Paper • 2608.13667 • Published • 13
Intern-S2-Mobius: Foundation Model with Decoupled Knowledge and Reasoning
Paper • 2608.14290 • Published • 31
Agents Catching Agents: Shortcut Cascades and Benchmark Gaming in Clinical Multi-Agent Systems
Paper • 2608.03744 • Published • 5
upvoted 5
papers 4 days ago
Thought-Level Beam Search for Reasoning
Paper • 2608.08020 • Published • 15
OmniScientist: An Omni-Modal Omni-Discipline AI Scientist
Paper • 2608.13558 • Published • 14
Full-bandwidth transformer
Paper • 2608.08888 • Published • 21
Massive Activations in Hybrid Linear Attention Large Language Models: Pre-Attention Spikes and Inter-Spike Plateaus
Paper • 2608.12149 • Published • 30
AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design
Paper • 2608.13560 • Published • 51