collaborators

7 papers

cs.CV2026

Think-as-You-See: Streaming Chain-of-Thought Reasoning for Large Vision-Language Models

Jialiang Zhang, Junlong Tong, Junyan Lin +4

Large Vision Language Models (LVLMs) exhibit strong Chain-of-Thought (CoT) capabilities, yet most existing paradigms assume full-video availability before inference, a batch-style…

cs.CL2026

Rethinking the Role of LLMs in Time Series Forecasting

Xin Qiu, Junlong Tong, Yirong Sun +3

Large language models (LLMs) have been introduced to time series forecasting (TSF) to incorporate contextual knowledge beyond numerical signals. However, existing studies question…

cs.CV2026

UTPTrack: Towards Simple and Unified Token Pruning for Visual Tracking

Hao Wu, Xudong Wang, Jialiang Zhang +5

One-stream Transformer-based trackers achieve advanced performance in visual object tracking but suffer from significant computational overhead that hinders real-time deployment. W…

cs.CV2026

HiDrop: Hierarchical Vision Token Reduction in MLLMs via Late Injection, Concave Pyramid Pruning, and Early Exit

Hao Wu, Yingqi Fan, Jinyang Dai +3

The quadratic computational cost of processing vision tokens in Multimodal Large Language Models (MLLMs) hinders their widespread adoption. While progressive vision token pruning o…

cs.AI2026

On-Policy Supervised Fine-Tuning for Efficient Reasoning

Anhao Zhao, Ziyang Chen, Junlong Tong +6

Large reasoning models (LRMs) are commonly trained with reinforcement learning (RL) to explore long chain-of-thought reasoning, achieving strong performance at high computational c…

cs.LG2025

The Few Govern the Many:Unveiling Few-Layer Dominance for Time Series Models

Xin Qiu, Junlong Tong, Yirong Sun +2

Large-scale models are at the forefront of time series (TS) forecasting, dominated by two paradigms: fine-tuning text-based Large Language Models (LLM4TS) and training Time Series…