Daniil Robnikov

daniilrobnikov's activity

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

upvoted 2 papers 4 days ago

Dynamic Chunking Diffusion Transformer

Paper • 2603.06351 • Published 8 days ago • 12

LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory

Paper • 2603.03269 • Published 11 days ago • 52

upvoted 3 papers 8 days ago

VGGT-Det: Mining VGGT Internal Priors for Sensor-Geometry-Free Multi-View Indoor 3D Object Detection

Paper • 2603.00912 • Published 14 days ago • 36

From Scale to Speed: Adaptive Test-Time Scaling for Image Editing

Paper • 2603.00141 • Published 18 days ago • 134

Track4World: Feedforward World-centric Dense 3D Tracking of All Pixels

Paper • 2603.02573 • Published 12 days ago • 11

upvoted 2 papers 12 days ago

InfoNCE Induces Gaussian Distribution

Paper • 2602.24012 • Published 15 days ago • 12

dLLM: Simple Diffusion Language Modeling

Paper • 2602.22661 • Published 17 days ago • 128

upvoted a paper 13 days ago

RoMa v2: Harder Better Faster Denser Feature Matching

Paper • 2511.15706 • Published Nov 19, 2025 • 9

upvoted 2 papers 17 days ago

Adam Improves Muon: Adaptive Moment Estimation with Orthogonalized Momentum

Paper • 2602.17080 • Published 24 days ago • 3

On the "Induction Bias" in Sequence Models

Paper • 2602.18333 • Published 22 days ago • 4

upvoted a paper 21 days ago

Unified Latents (UL): How to train your latents

Paper • 2602.17270 • Published 23 days ago • 57

upvoted 3 papers 25 days ago

UniWeTok: An Unified Binary Tokenizer with Codebook Size 2^{128} for Unified Multimodal Large Language Model

Paper • 2602.14178 • Published 27 days ago • 13

FLAC: Maximum Entropy RL via Kinetic Energy Regularized Bridge Matching

Paper • 2602.12829 • Published 29 days ago • 4

Conversational Image Segmentation: Grounding Abstract Concepts with Scalable Supervision

Paper • 2602.13195 • Published 29 days ago • 4

upvoted 2 papers 28 days ago

Stroke of Surprise: Progressive Semantic Illusions in Vector Sketching

Paper • 2602.12280 • Published 30 days ago • 32

MOSS-Audio-Tokenizer: Scaling Audio Tokenizers for Future Audio Foundation Models

Paper • 2602.10934 • Published Feb 11 • 49

upvoted 4 papers about 1 month ago

OmniMoE: An Efficient MoE by Orchestrating Atomic Experts at Scale

Paper • 2602.05711 • Published Feb 5 • 11

LLaDA2.1: Speeding Up Text Diffusion via Token Editing

Paper • 2602.08676 • Published Feb 9 • 70

A2Eval: Agentic and Automated Evaluation for Embodied Brain

Paper • 2602.01640 • Published Feb 2 • 8

Residual Context Diffusion Language Models

Paper • 2601.22954 • Published Jan 30 • 35