16 papers
TIP: Token Importance in On-Policy Distillation
Yuanda Xu, Hejian Sang, Zhengze Zhou +3
On-policy knowledge distillation (OPD) trains a student on its own rollouts under token-level supervision from a teacher. Not all token positions matter equally, but existing views…
UniPrefill: Universal Long-Context Prefill Acceleration via Block-wise Dynamic Sparsification
Qihang Fan, Huaibo Huang, Zhiying Wu +2
As large language models (LLMs) continue to advance rapidly, they are becoming increasingly capable while simultaneously demanding ever-longer context lengths. To improve the infer…
Advancing Vision Transformer with Enhanced Spatial Priors
Qihang Fan, Huaibo Huang, Mingrui Chen +2
In recent years, the Vision Transformer (ViT) has garnered significant attention within the computer vision community. However, the core component of ViT, Self-Attention, lacks exp…
HalluClear: Diagnosing, Evaluating and Mitigating Hallucinations in GUI Agents
Chao Jin, Wenkui Yang, Hao Sun +6
While progress in GUI agents has been largely driven by industrial-scale training, ungrounded hallucinations often trigger cascading failures in real-world deployments.Unlike gener…
MVPBench: A Multi-Video Perception Evaluation Benchmark for Multi-Modal Video Understanding
Purui Bai, Tao Wu, Jiayang Sun +3
The rapid progress of Large Language Models (LLMs) has spurred growing interest in Multi-modal LLMs (MLLMs) and motivated the development of benchmarks to evaluate their perceptual…
Think 360°: Evaluating the Width-centric Reasoning Capability of MLLMs Beyond Depth
Mingrui Chen, Hexiong Yang, Haogeng Liu +2
In this paper, we present a holistic multimodal benchmark that evaluates the reasoning capabilities of MLLMs with an explicit focus on reasoning width, a complementary dimension to…