16 citations · 41 across the 23 of their papers we have counts for
13 papers · 1 filter
TwinPrune: Density-Aware Two-Phase Token Pruning for Vision-Language Models
Kai Liu, Anqi Li, Junxian Li +4
We propose a unified spatial-density signal to score token importance for both inference phases: bipartite merge for prefill and KV eviction for decode, yielding measurable gains i…
Fewer Tokens, More Self-Teaching: On-Policy Self-Distillation for Extreme Visual Token Reduction
Junxian Li, Ruixuan Yang, Tianao Zhang +3
Visual token reduction is an effective way to accelerate multimodal large language models (MLLMs), but performance deteriorates rapidly under extremely low token budgets. Existing…
ET-Prune: Evidence-Aware Dynamic Budgeting for Visual Token Pruning in Text-Rich MLLMs
Zizhong Ding, Junxian Li, Kai Liu +4
Visual token pruning reduces the inference cost of multimodal large language models, but a fixed token ratio is poorly matched to text-rich inputs. In OCR-centric tasks, decisive e…
TurboClear: One-Step Object-Effect Removal via Region-Calibrated Distribution Matching and Fusion
Jiawei Guo, Junxian Li, Yixin Tang +4
Recently, diffusion-based removal methods have achieved promising visual quality in removing both target objects and their associated effects. However, they typically rely on multi…
Cross-Branch Conflict as a Shield: Safeguarding Facial Identities in Unified Multimodal Image Editing
Weiwei Tan, Junxian Li, Rui Wang +3
Unified multimodal models (UMMs) have recently demonstrated powerful instruction-based image editing capabilities, while also raising serious concerns about the unauthorized manipu…
PermuQuant: Lowering Per-Group Quantization Error by Reordering Channels for Diffusion Models
Yongsen Cheng, Kai Liu, Kaiwen Tao +5
Large-scale visual generative models have achieved remarkable performance. However, their high computational and memory costs make deployment challenging in resource-constrained sc…
GTR: Generation-Guided Visual Token Reduction for Separate-Encoder Unified Multimodal Models
Junxian Li, Kai Liu, Zizhong Ding +4
The development of separate-encoder Unified multimodal models (UMMs) comes with a rapidly growing inference cost due to dense visual token processing. In this paper, we focus on un…
FlashClear: Ultra-Fast Image Content Removal via Efficient Step Distillation and Feature Caching
Yixin Tang, Jiawei Guo, Junxian Li +6
Recently, diffusion-based object removal models have achieved impressive results in eliminating objects and their associated visual effects. However, they indiscriminately denoise…
StreamMeCo: Long-Term Agent Memory Compression for Efficient Streaming Video Understanding
Junxi Wang, Te Sun, Jiayi Zhu +6
Vision agent memory has shown remarkable effectiveness in streaming video understanding. However, storing such memory for videos incurs substantial memory overhead, leading to high…
PlanViz: Evaluating Planning-Oriented Image Generation and Editing for Computer-Use Tasks
Junxian Li, Kai Liu, Leyang Chen +7
Unified multimodal models (UMMs) have shown impressive capabilities in complex natural image generation. However, their potential in computer-use planning tasks, which are closely…
S-MLLM: Boosting Spatial Reasoning Capability of MLLMs for 3D Visual Grounding with Structural Guidance
Beining Xu, Siting Zhu, Zhao Jin +2
3D Visual Grounding (3DVG) focuses on locating objects in 3D scenes based on natural language descriptions, serving as a fundamental task for embodied AI and robotics. Recent advan…
IAG: Input-aware Backdoor Attack on VLM-based Visual Grounding
Junxian Li, Beining Xu, Simin Chen +4
Recent advances in vision-language models (VLMs) have significantly enhanced the visual grounding task, which involves locating objects in an image based on natural language querie…
Critic-V: VLM Critics Help Catch VLM Errors in Multimodal Reasoning
Di Zhang, Junxian Li, Jingdi Lei +10
Vision-language models (VLMs) have shown remarkable advancements in multimodal reasoning tasks. However, they still often generate inaccurate or irrelevant responses due to issues…