Rethinking Token-Level Policy Optimization for Multimodal Chain-of-Thought
Paper • 2603.22847 • Published • 25
AI & ML interests
Video Understanding, Audio-Visual, Multimodal LLMs, Video Captioning, Instruction Tuning, Dataset Curation, Qwen-based, Open-source, Fully-Open-MLLMs
Recent Activity
View all activity
Papers
View all Papers
lyhisme
submitted a
paper to Daily Papers 10 days ago
lyhisme
updated 2
models 24 days ago
lyhisme
updated a
dataset 24 days ago
lyhisme
updated a
Space 24 days ago
lyhisme
submitted a
paper to Daily Papers about 2 months ago
lyhisme
published 2
models about 2 months ago
lyhisme
published a
Space about 2 months ago
lyhisme
published a
dataset about 2 months ago
lyhisme
authored 5
papers 6 months ago
TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs
Paper • 2509.18056 • Published • 27
Cascade-CLIP: Cascaded Vision-Language Embeddings Alignment for Zero-Shot Semantic Segmentation
Paper • 2406.00670 • Published
Unbiased Region-Language Alignment for Open-Vocabulary Dense Prediction
Paper • 2412.06244 • Published
A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models
Paper • 2508.01548 • Published • 14
Revisiting Efficient Semantic Segmentation: Learning Offsets for Better Spatial and Class Feature Alignment
Paper • 2508.08811 • Published • 2