MOSS-Video-Preview: Toward Real-Time Video Understanding via Cross-Attention Paper • 2606.07639 • Published Jun 1 • 5
Sparser Block-Sparse Attention via Token Permutation Paper • 2510.21270 • Published Oct 24, 2025 • 25
UnifiedVisual: A Framework for Constructing Unified Vision-Language Datasets Paper • 2509.14738 • Published Sep 18, 2025
Advancing Fine-Grained Visual Understanding with Multi-Scale Alignment in Multi-Modal Models Paper • 2411.09691 • Published Nov 14, 2024
UnifiedMLLM: Enabling Unified Representation for Multi-modal Multi-tasks With Large Language Model Paper • 2408.02503 • Published Aug 5, 2024
SpeechAlign: Aligning Speech Generation to Human Preferences Paper • 2404.05600 • Published Apr 8, 2024 • 1
BitStack: Fine-Grained Size Control for Compressed Large Language Models in Variable Memory Environments Paper • 2410.23918 • Published Oct 31, 2024 • 21
DenoSent: A Denoising Objective for Self-Supervised Sentence Representation Learning Paper • 2401.13621 • Published Jan 24, 2024 • 1
Case2Code: Learning Inductive Reasoning with Synthetic Data Paper • 2407.12504 • Published Jul 17, 2024 • 8
InferAligner: Inference-Time Alignment for Harmlessness through Cross-Model Guidance Paper • 2401.11206 • Published Jan 20, 2024 • 2
SpeechAgents: Human-Communication Simulation with Multi-Modal Multi-Agent Systems Paper • 2401.03945 • Published Jan 8, 2024
SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities Paper • 2305.11000 • Published May 18, 2023 • 5