InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editing
Paper
• 2603.09877 • Published
• 24
HoT
university
AI & ML interests
nlp vision xai
Recent Activity
View all activity
taesiri
submitted a paper to Daily Papers about 22 hours ago
taesiri
submitted 4 papers to Daily Papers about 23 hours ago
A Text-Native Interface for Generative Video Authoring
Paper
• 2603.09072 • Published
MiniAppBench: Evaluating the Shift from Text to Interactive HTML Responses in LLM-Powered Assistants
Paper
• 2603.09652 • Published
• 7
Towards a Neural Debugger for Python
Paper
• 2603.09951 • Published
• 1
Fish Audio S2 Technical Report
Paper
• 2603.08823 • Published
• 12
taesiri
submitted 3 papers to Daily Papers 2 days ago
taesiri
submitted 5 papers to Daily Papers 3 days ago
Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders
Paper
• 2603.06569 • Published
• 95
Reasoning Models Struggle to Control their Chains of Thought
Paper
• 2603.05706 • Published
• 25
Physical Simulator In-the-Loop Video Generation
Paper
• 2603.06408 • Published
• 10
Dynamic Chunking Diffusion Transformer
Paper
• 2603.06351 • Published
• 12
FlashPrefill: Instantaneous Pattern Discovery and Thresholding for Ultra-Fast Long-Context Prefilling
Paper
• 2603.06199 • Published
• 9
taesiri
submitted 5 papers to Daily Papers 6 days ago
UltraDexGrasp: Learning Universal Dexterous Grasping for Bimanual Robots with Synthetic Data
Paper
• 2603.05312 • Published
• 7
RealWonder: Real-Time Physical Action-Conditioned Video Generation
Paper
• 2603.05449 • Published
• 11
Distribution-Conditioned Transport
Paper
• 2603.04736 • Published
• 2
Timer-S1: A Billion-Scale Time Series Foundation Model with Serial Scaling
Paper
• 2603.04791 • Published
• 16
KARL: Knowledge Agents via Reinforcement Learning
Paper
• 2603.05218 • Published
• 6
taesiri
submitted 2 papers to Daily Papers 7 days ago