12 papers
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…
Next Thoughts Are Distributions: Generative Autoregressive Reasoning in the Latent Space
Yang Li, Yi Wang, Shiyuan Huang +3
Reasoning problems often admit multiple valid ways to proceed. Continuous reasoning promises to move computation beyond language tokens into a more compact latent space, but repres…
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…
LACE: Lattice Attention for Cross-thread Exploration
Yang Li, Zirui Zhang, Yang Liu +1
Current large language models reason in isolation. Although it is common to sample multiple reasoning paths in parallel, these trajectories do not interact, and often fail in the s…
Electrostatic Photoluminescence Tuning in All-Solid-State Perovskite Transistors
Vladimir Bruevich, Dmitry Maslennikov, Beier Hu +2
We demonstrate an all solid state semiconductor device, based on epitaxial single crystalline metal halide perovskites, enabling reversible control of a perovskite photoluminescenc…
APPLV: Adaptive Planner Parameter Learning from Vision-Language-Action Model
Yuanjie Lu, Beichen Wang, Zhengqi Wu +4
Autonomous navigation in highly constrained environments remains challenging for mobile robots. Classical navigation approaches offer safety assurances but require environment-spec…
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…
Aligned but Blind: Alignment Increases Implicit Bias by Reducing Awareness of Race
Lihao Sun, Chengzhi Mao, Valentin Hofmann +1
Although value-aligned language models (LMs) appear unbiased in explicit bias evaluations, they often exhibit stereotypes in implicit word association tasks, raising concerns about…