15 papers
PN-Mix: Pair-Norm Guided Mixed-Precision Key Cache Quantization for Efficient Long-Output LLM Inference
Gil Jae Song, Sungjoo Yoo
Long-output inference in large language models suffers from severe KV cache memory and bandwidth bottlenecks. While KV cache quantization alleviates this issue, low-bit quantizatio…
Spatial Memory Intelligence: Endowing World Models with Understanding-Driven Long-Term Memory
Ying Yang, Guiyu Zhang, Lianghua Huang +5
Long-video generation and world models have shown strong potential for interactive entertainment and embodied simulation by predicting future observations conditioned on user actio…
GIFTBench: Diagnosing Generalization in Image Forgery Localization and Informing Model Design
Baoke Dou, Ziye Wang, Hao Wang +5
Reliable evaluation of image forgery localization (IFL) requires assessing models under diverse distribution changes, yet existing benchmarks often cover limited manipulation condi…
CoSec: Benchmarking Agent Security in Communities
Hao Chen, Wenhui Dong, Ye Chen +12
LLM agents operate in persistent collaborative environments involving multiple users, communities, memories, files, and tools. Community boundaries may remain fixed or evolve with…
MME-Safety: A Fine-grained Benchmark for Safety Evaluation of MLLMs
Yilian Shi, Yueming Lyu, Haoxiang Tan +5
While Multimodal Large Language Models (MLLMs) show remarkable advancements, their cross-modal capabilities introduce complex vulnerabilities that easily bypass unimodal filters. E…
PRMU: A Corpus-Free Benchmark for Person-Centric Knowledge Unlearning in Multimodal Large Language Models
Huafeng Chen, Yueming Lyu, Ziyuan Chen +4
Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in storing and recalling rich person-related knowledge, raising increasing concerns about reliabl…
Is There Really a Camouflaged Object? Towards Realistic Camouflaged Object Detection
Huafeng Chen, Yueming Lyu, Chenyang Si +3
Camouflaged object detection (COD) aims to segment objects that are visually concealed in their surroundings and has attracted increasing attention in recent years. However, most e…
AURORA-LM: Autoencoding Unified Representation for Continuous-Latent Diffusion Language Modeling
Jiajun Liang, Yucheng Liao, Yukang Cao +12
Language remains an outlier in generative modeling: while images, video, and audio are increasingly modeled in continuous latent spaces, text generation still relies predominantly…
TOBench: A Task-Oriented Omni-Modal Benchmark for Real-World Tool-Using Agents
Zhiqiang Liu, Wenhui Dong, Yilang Tan +3
Tool-using agents are increasingly expected to operate across realistic professional workflows, where they must interpret multimodal inputs, coordinate external tools, inspect inte…
NGM: A Plug-and-Play Training-Free Memory Module for LLMs
Yuwen Qu, Wenhui Dong, Chenyang Si +3
Recent studies have introduced memory-augmented architectures that decouple knowledge storage from neural computation, enabling more direct access to stored representations. Howeve…
One-to-More: High-Fidelity Training-Free Anomaly Generation with Attention Control
Haoxiang Rao, Zhao Wang, Chenyang Si +4
Industrial anomaly detection (AD) is characterized by an abundance of normal images but a scarcity of anomalous ones. Although numerous few-shot anomaly synthesis methods have been…
NOVA: Sparse Control, Dense Synthesis for Pair-Free Video Editing
Tianlin Pan, Jiayi Dai, Chenpu Yuan +7
Recent video editing models have achieved impressive results, but most still require large-scale paired datasets. Collecting such naturally aligned pairs at scale remains highly ch…
StableWorld: Towards Stable and Consistent Long Interactive Video Generation
Ying Yang, Zhengyao Lv, Yujia Zeng +9
In this paper, we explore the overlooked challenge of stability and temporal consistency in interactive video generation, which synthesizes dynamic and controllable video worlds th…
PosterCopilot: Toward Layout Reasoning and Controllable Editing for Professional Graphic Design
Jiazhe Wei, Ken Li, Tianyu Lao +4
Graphic design forms the cornerstone of modern visual communication, serving as a vital medium for promoting cultural and commercial events. Recent advances have explored automatin…
DiverseAR: Boosting Diversity in Bitwise Autoregressive Image Generation
Ying Yang, Zhengyao Lv, Tianlin Pan +5
In this paper, we investigate the underexplored challenge of sample diversity in autoregressive (AR) generative models with bitwise visual tokenizers. We first analyze the factors…