cs.CV · 2026-11-02 · No. 161
Computer Vision and Pattern Recognition, 2026-11-02.
10 new papers in cs.CV. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
10 entries-
01
Latent Reasoning in Continuous Space for Unified Multimodal Models
Byungwoo Jeon, Yoonwoo Jeong, Hyunseok Lee, Minsu Cho, Jinwoo Shin
cs.CV · cs.CL · cs.LG
Unified Multimodal Models (UMMs) achieve remarkable success on diverse multimodal understanding and generation tasks, yet they still struggle to effectively leverage language-based chain-of-thought reasoning for image generation. As a result, existing reasoning-augmented UMMs often fail to inherit the test-time scaling and fine-grained controllability observed in large language models. We attribute this failure to a fundamental modality...
-
02
A Better Critic Matters for Distribution Matching Distillation
Zongze Wu, Xianbang Wang, Zhengyang Geng, Mingdeng Cao, Zhoutong Zhang, Richard Zhang, Eli Shechtman, Ruiming Cao
cs.CV · cs.LG
Distribution Matching Distillation (DMD) trains a few-step student using the difference between a teacher's score and an online critic's estimate of the student distribution's score. We investigate what the critic needs, in capacity and in information, to provide a reliable training signal. On the capacity side, controlled experiments across seven SiT model sizes on ImageNet show that increasing teacher size while keeping a small critic fixed...
-
03
Learning Clean Generative Processes from Noisy Measurements
Fabian Kruse, Lorenzo Baldassari, Ivan Dokmanić
cs.CV · cs.AI · cs.LG
We study how to learn a generative model of clean images using only noisy observations. Diffusion processes and their generalizations to non-Gaussian noise require posterior predictions at every noise level. We first show that it is possible to learn these predictions from independent noisy views using Noise2Noise regression, but only at or above the noise level of the training data. To learn the predictions below that level, needed to...
-
04
Different Models, Shared Failures: Auditing Frozen-Encoder Pools for Medical Segmentation
Eunseob Choi, Kyeonghun Kim, Hyuk-Jae Lee, Nam-Joon Kim
cs.CV · cs.AI
Average segmentation accuracy and model count do not reveal whether models fail on the same cases. We present CoFailMed, an audit of correlated failures in pretrained-encoder pools for medical segmentation. Across five 2D tasks, we evaluate 11 public pretrained encoders (a controlled sample, not a census) using frozen features and separately trained $1\times 1$ readouts with four seeds per encoder. Shared-checkpoint pairs have the highest...
-
05
OT-CAL: Optimal-Transport-Guided Adaptive Sample Selection for Efficient Visual Learning
Suryansh Talukdar, Jin Soung Yoo
cs.CV · cs.AI
Deep neural networks for image recognition are typically trained using mini-batches, with a forward pass to compute predictions and losses followed by a more computationally expensive backward pass to update model parameters. However, not all training samples contribute equally to learning, suggesting that computation can be reduced by performing backward passes only on informative samples. The challenge is that sample informativeness changes...
-
06
GRIT: Gradient Masking for Visually Misgrounded Tokens in Text-Rich Reasoning
Chanseul Cho, Noori Bae, Dongheon Lee, Youngmin Ro
cs.CV · cs.AI · cs.CL
Reinforcement learning with verifiable rewards (RLVR) has recently been extended to vision-language models (VLMs), yet its effectiveness remains limited for text-rich reasoning tasks. We highlight a key factor contributing to this limitation: models frequently arrive at correct final answers despite misperceiving visual information during intermediate steps. We define this phenomenon as Correct-but-Visually-Misgrounded Reasoning (CVMR)....
-
07
Attention Maps Know When to Think: Training-Free Difficulty-Aware Chain-of-Thought for Reasoning Segmentation
Chanseul Cho, Jaesung Jun, Dongheon Lee, Youngmin Ro
cs.CV · cs.AI
Chain-of-Thought (CoT) prompting has become a standard reasoning strategy in Multi-modal Large Language Models (MLLMs), showing strong performance in complex vision-language tasks such as reasoning segmentation. However, our analysis reveals that indiscriminate CoT usage can lead to degraded performance by inducing unnecessary reasoning, a phenomenon we term overthinking. In reasoning segmentation, overthinking often leads to misalignment...
-
08
SACQ: Structure-Aware Codebook Quantization for Ultra-Low-Bit Vision-Language-Action Models
Haesung Lee, Insu Han
cs.CV · cs.LG · cs.RO
Vision-Language-Action (VLA) models enable capable robot behavior, but their large memory footprint limits deployment on resource-constrained robotic platforms. Weight quantization is a natural remedy, yet post-training quantization (PTQ) recipes inherited from large language models degrade when applied to VLAs at ultra-low precision. Existing low-bit PTQ methods often fail to explicitly account for the structure of downstream operations and...
-
09
DUGO: Dual-Scale Gaussian Memory for Online Temporal Action Localization in Egocentric Procedural Videos
Mohammed Aman Bhuiyan, Md. Sazzad Hossain Adib, Samiul Basir Bhuiyan, Mir Faiyaz Hossain, Syed Mohammed Shamsul...
cs.CV · cs.LG
Online Temporal Action Localization (OnTAL) aims to detect and localize action instances from untrimmed streaming videos in real time. Unlike offline approaches, OnTAL models have no access to future frames and cannot go back and refine earlier predictions, which makes the task considerably harder given the strict real-time constraints and narrow temporal window available. Most existing OnTAL methods lean on either brief anchor-based context...
-
10
GenDSR: Transferring Representations from Video Generation Models for Dynamic Spatial Reasoning
Ke Yang, Zhenyu Zhang, Jun Li
cs.CV · cs.AI
Dynamic spatial reasoning is essential for connecting visual intelligence to thephysical world, yet remains challenging for vision-language models (VLMs), which must preserve scene state while tracking how spatial relations evolve over time. Meanwhile, video generation models (VGMs), trained to synthesize temporally coherent world dynamics, offer a rich source of spatiotemporal representations. We present GenDSR, a framework that transfers...
This edition is part of The Daily Abstract — cs.CV archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.