SEGA: Spectral-Energy Guided Attention for Resolution Extrapolation in Diffusion Transformers
Paper • 2605.22668 • Published • 31
Prithiv Sakthi PRO
prithivMLmods
AI & ML interests
computer vision, nlp, multimodality
- HuggingFace Fellow ML 🤗
Recent Activity
upvoted a paper about 6 hours ago
SEGA: Spectral-Energy Guided Attention for Resolution Extrapolation in Diffusion Transformers upvoted a paper about 6 hours ago
PhysX-Omni: Unified Simulation-Ready Physical 3D Generation for Rigid, Deformable, and Articulated Objects liked a model about 6 hours ago
prithivMLmods/Qwen3-VL-8B-Heretic-StableOrganizations
upvoted 2
papers about 6 hours ago
upvoted a collection about 15 hours ago
upvoted 2
changelogs about 23 hours ago
Hugging Face Changelog
Copy Repo Contents to Buckets Instantly
• 26
Hugging Face Changelog
Filter Leaderboards by Model Size
• 95
upvoted 4
papers 1 day ago
Sensor2Sensor: Cross-Embodiment Sensor Conversion for Autonomous Driving
Paper • 2605.22809 • Published • 23
KVServe: Service-Aware KV Cache Compression for Communication-Efficient Disaggregated LLM Serving
Paper • 2605.13734 • Published • 10
Swift Sampling: Selecting Temporal Surprises via Taylor Series
Paper • 2605.22678 • Published • 6
Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention
Paper • 2605.22791 • Published • 21
upvoted 3
papers 7 days ago
VGGT-Edit: Feed-forward Native 3D Scene Editing with Residual Field Prediction
Paper • 2605.15186 • Published • 26
MemEye: A Visual-Centric Evaluation Framework for Multimodal Agent Memory
Paper • 2605.15128 • Published • 60
Self-Distilled Agentic Reinforcement Learning
Paper • 2605.15155 • Published • 108
upvoted a collection 8 days ago
upvoted 2
articles 11 days ago
Article
DeepSeek-V4: a million-token context that agents can actually use
burtenshaw
• • 46 Article
Building Blocks for Foundation Model Training and Inference on AWS
amazon
• • 21 upvoted a paper 11 days ago
upvoted 3
papers 13 days ago
HyperEyes: Dual-Grained Efficiency-Aware Reinforcement Learning for Parallel Multimodal Search Agents
Paper • 2605.07177 • Published • 61
TextLDM: Language Modeling with Continuous Latent Diffusion
Paper • 2605.07748 • Published • 26
HumanNet: Scaling Human-centric Video Learning to One Million Hours
Paper • 2605.06747 • Published • 51
upvoted a collection 14 days ago