7 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…
StochasT: Learning with Stochastic Turn Depth for Visual Instruction Tuning
Yuan Qing, Chengzhi Mao, Boqing Gong
Large Vision-Language Models (LVLMs) rely extensively on Visual Instruction Tuning (VIT) to elicit their multimodal reasoning capabilities. However, we find a discrepancy: VIT ofte…
Language-Instructed Vision Embeddings for Controllable and Generalizable Perception
Chengzhi Mao, Xudong Lin, Wen-Sheng Chu
Vision foundation models are typically trained as static feature extractors, placing the burden of task adaptation onto large downstream models. We propose an alternative paradigm:…
SCOPE: Self-Supervised Concept Discovery via Preference Learning
Shilong Xiang, Zirui Zhang, Chengzhi Mao
Self-supervised learning can learn useful representations from unlabeled images. Yet these representations remain largely opaque, making it difficult to understand what visual conc…
SSD: Spatially Speculative Decoding Accelerates Autoregressive Image Generation
Shilong Xiang, Zirui Zhang, Lijun Yu +1
Autoregressive image models treat images as 1D token sequences, inheriting the next-token factorization of language models. This flattening discards a useful property of images: vi…
Differences That Matter: Auditing Models for Capability Gap Discovery and Rectification
Qihao Liu, Chengzhi Mao, Yaojie Liu +2
Conventional evaluation methods for multimodal LLMs (MLLMs) lack interpretability and are often insufficient to fully disclose significant capability gaps across models. To address…
Mull-Tokens: Modality-Agnostic Latent Thinking
Arijit Ray, Ahmed Abdelkader, Chengzhi Mao +5
Reasoning goes beyond language; the real world requires reasoning about space, time, affordances, and much more that words alone cannot convey. Existing multimodal models exploring…