1 citations · 2 across the 16 of their papers we have counts for
16 papers · 1 filter
LVMH: A Meta-Optimization Harness for Long-Video Agent Memory
Liwei Che, Benlin Liu, Dai Li +7
Long-video agents must map hours or days of multimodal evidence into a bounded context while respecting token and latency budgets, making memory design a context-management challen…
Why MLLMs Struggle to Count: Overcoming Individuation and Aggregation Bottlenecks with ConvStack
Liwei Che, Yihao Quan, Sen Fang +4
Multimodal Large Language Models (MLLMs) consistently struggle with fine-grained visual counting, yet the underlying causes remain poorly understood. In this work, we present a mec…
When Seeing Overrides Knowing: Visual Dominance and Deferral-Based Method for Personalized Safety in VLMs
Edward Sun, Yuchen Wu, Zixian Ma +7
Vision-language models (VLMs) are increasingly deployed in high-stakes settings, where a response that is reasonable in general may still be unsafe for a particular user whose medi…
PerceptionComp: A Video Benchmark for Complex Perception-Centric Reasoning
Shaoxuan Li, Zhixuan Zhao, Hanze Deng +9
We introduce PerceptionComp, a manually annotated benchmark for complex, long-horizon, perception-centric video reasoning. PerceptionComp is designed so that no single moment is su…
Counting Circuits: Mechanistic Interpretability of Visual Reasoning in Large Vision-Language Models
Liwei Che, Zhiyu Xue, Yihao Quan +7
Counting serves as a simple but powerful test of a Large Vision-Language Model's (LVLM's) reasoning; it forces the model to identify each individual object and then add them all up…
CapNav: Benchmarking Vision Language Models on Capability-conditioned Indoor Navigation
Xia Su, Ruiqi Chen, Benlin Liu +4
Vision-Language Models (VLMs) have shown remarkable progress in Vision-Language Navigation (VLN), offering new possibilities for navigation decision-making that could benefit both…
OmniView: An All-Seeing Diffusion Model for 3D and 4D View Synthesis
Xiang Fan, Sharath Girish, Vivek Ramanujan +6
Prior approaches injecting camera control into diffusion models have focused on specific subsets of 4D consistency tasks: novel view synthesis, text-to-video with camera control, i…
GenEval 2: Addressing Benchmark Drift in Text-to-Image Evaluation
Amita Kamath, Kai-Wei Chang, Ranjay Krishna +3
Automating Text-to-Image (T2I) model evaluation is challenging; a judge model must be used to score correctness, and test prompts must be selected to be challenging for current T2I…
Structure From Tracking: Distilling Structure-Preserving Motion for Video Generation
Yang Fei, George Stoica, Jingyuan Liu +4
Reality is a dance between rigid constraints and deformable structures. For video models, that means generating motion that preserves fidelity as well as structure. Despite progres…
Visual Representations inside the Language Model
Benlin Liu, Amita Kamath, Madeleine Grunde-McLaughlin +2
Despite interpretability work analyzing VIT encoders and transformer activations, we don't yet understand why Multimodal Language Models (MLMs) struggle on perception-heavy tasks.…
Reinforced Visual Perception with Tools
Zetong Zhou, Dongping Chen, Zixian Ma +6
Visual reasoning, a cornerstone of human intelligence, encompasses complex perceptual and logical processes essential for solving diverse visual problems. While advances in compute…
MultiRef: Controllable Image Generation with Multiple Visual References
Ruoxi Chen, Dongping Chen, Siyuan Wu +6
Visual designers naturally draw inspiration from multiple visual references, combining diverse elements and aesthetic principles to create artwork. However, current image generativ…
RefTok: Reference-Based Tokenization for Video Generation
Xiang Fan, Xiaohang Sun, Kushan Thakkar +4
Effectively handling temporal redundancy remains a key challenge in learning video models. Prevailing approaches often treat each set of frames independently, failing to effectivel…
Interleaved Scene Graphs for Interleaved Text-and-Image Generation Assessment
Dongping Chen, Ruoxi Chen, Shu Pu +8
Many real-world user queries (e.g. "How do to make egg fried rice?") could benefit from systems capable of generating responses with both textual steps with accompanying images, si…
Coarse Correspondences Boost Spatial-Temporal Reasoning in Multimodal Language Model
Benlin Liu, Yuhao Dong, Yiqin Wang +6
Multimodal language models (MLLMs) are increasingly being applied in real-world environments, necessitating their ability to interpret 3D spaces and comprehend temporal dynamics. C…
Efficient Inference of Vision Instruction-Following Models with Elastic Cache
Zuyan Liu, Benlin Liu, Jiahui Wang +5
In the field of instruction-following large vision-language models (LVLMs), the efficient deployment of these models faces challenges, notably due to the high memory demands of the…