Benchmarks and evaluation

Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.

28,111 stories · RSS feed

arXiv Computer Vision

Oct 26

TileShare: Training-Free Acceleration of Overlapping Tiled ViT Decoding

arXiv:2610.32233v1 Announce Type: new Abstract: Fixed-window Vision Transformer (ViT) decoders run at deployment resolution as overlapping tiles: every token in an overlap band is processed by severa...

By Xiangzhong Ye, Zhongshen Li, Shen You, Ziyang Meng, Liang Xu, Junkai Ji, Qiuzhen Lin, Xiangtao Li, Ka-Chun Wong

llms computer-vision efficiency benchmarks

arXiv Computer Vision

Oct 26

Polyp-VSSD: A Pre-trained Transformer with Local-Global Joint VSSD Decoding for Polyp Segmentation

arXiv:2610.32282v1 Announce Type: new Abstract: Early detection of colorectal polyps is essential for preventing colorectal cancer, making accurate polyp segmentation a key component in computer-aide...

By Xiaobo Zhu, Shiwei Wu, Yu An, Yuechen Tao, He Sun, Song Zhang, Zhenyu Liu

llms computer-vision benchmarks

arXiv Computer Vision

Oct 26

Learning Fine-Grained Visual Classification with Text as Privileged Information via Multimodal Distillation

arXiv:2610.32442v1 Announce Type: new Abstract: Fine-grained visual classification (FGVC) requires distinguishing between highly similar categories by focusing on subtle, localized visual differences...

By Aishwarya Venkataramanan, Christian Ickler, Joachim Denzler

efficiency multimodal benchmarks

arXiv Computer Vision

Oct 26

PROVE: Probabilistic Visual Grounding via Patch-Level Evidence for Vision-Language Models

arXiv:2610.32440v1 Announce Type: new Abstract: Visual grounding with vision-language models such as CLIP typically produces a single deterministic relevance map for an image-query pair, without indi...

By Mayank Nautiyal, Tianru Zhang, Li Ju, Ekta Vats, Prashant Singh

llms multimodal benchmarks

arXiv Computer Vision

Oct 26

PCFBench: How Far Can Large Vision-Language Models Go in Physics-aware Photonic Inverse Design?

arXiv:2610.32485v1 Announce Type: new Abstract: Photonic crystal fibers (PCFs) underpin critical applications in telecommunications, sensing, and high-power laser delivery, yet their design remains a...

By Shengchao Chen, Ting Shu, Sufen Ren

llms agents multimodal benchmarks

arXiv Computer Vision

Oct 26

Distortion-Aware Spatiotemporal Learning for Real-Time Wide-Angle Video Rectification

arXiv:2610.32500v1 Announce Type: new Abstract: While wide-angle lenses provide an expanded field of view (FoV), they exhibit severe nonlinear distortion near image boundaries, unnaturally stretching...

By Lang Nie, Yihan Yang, Wenbo Nie, Hongguang Zhu, Yang Wei, Chunyu Lin, Bin Xiao

benchmarks safety

arXiv Computer Vision

Oct 26

VERA-Hand: A Verified Multidimensional Benchmark for 2D Hand Pose Estimation in Third-Person Dynamic Gesture Videos

arXiv:2610.32517v1 Announce Type: new Abstract: Hand landmarks serve as input for gesture recognition, sign language understanding, and touchless human-computer interaction. Yet hand pose estimators...

By Gibran Benitez-Garcia, Hiroki Takahashi

computer-vision benchmarks

arXiv Computer Vision

Oct 26

The Answer Knows Where to Look: Zooming before MLLMs Answer under Visual-Token Budgets

arXiv:2610.32664v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) read images through visual tokens, and under the small per-image budgets that efficient deployment requires, t...

By Zhensheng Hu, Guanglong Xu, Guanqiang Hu

llms multimodal benchmarks

arXiv Computer Vision

Oct 26

Video-MemComp: Taylor-Guided Sensitivity-Aware Memory Management for Streaming Video Understanding

arXiv:2610.32784v1 Announce Type: new Abstract: The rapid growth of video data has created an urgent need for efficient video understanding systems that can handle long and continuous visual inputs,...

By Yonghui Niu, Yuhao Ji, Chang Nie, Jiao Zhang, Yilong Li, Junlan Feng, Ran He, Caifeng Shan, Chaoyou Fu

llms efficiency multimodal benchmarks safety

arXiv Computer Vision

Oct 26

LoCA: Enabling Multi-Modality in Geospatial Location Encoders

arXiv:2610.32894v1 Announce Type: new Abstract: Location encoders map geographic coordinates to high-dimensional descriptors through contrastive alignment with paired Earth Observation imagery. We pr...

By Panagiotis Koromilas, Eleanna Vali, Diogenis Antonopoulos, Eleni Saka, Dimitris Christofis, Nikolaos Ioannis Bountos, Konstantin Klemmer, Ioannis Papoutsis, Yannis Panagakis, Mihalis A. Nicolaou

rag multimodal benchmarks safety

arXiv Computer Vision

Oct 26

See What I Need, Dream What I Want: A Navigation Foundation Model on a Self-Constructed Representation Space

arXiv:2610.31762v1 Announce Type: cross Abstract: What visual representation should a navigation policy act on? Navigation policies built on vision foundation models largely leave representation desi...

By Jiawei Chen, Yinxi Wang, Zihan Yang, Meijun Gao, Yaowei Liu, Shuming Zhang, Zecheng Li, Xiangju Mi, Yuxuan Liu, Runzhong Huang, Tianlin Li, Xun Zhang, Zhengyang Wang, Xu Miao, Tong Yang

llms rag robotics benchmarks

arXiv Computer Vision

Oct 26

VisFlow: Interpretable Flow Matching for Visibility Reconstruction, Characterization, and Recognition

arXiv:2610.31892v1 Announce Type: cross Abstract: Methods for learning continuous representations, such as latent manifolds, are fundamental and ubiquitous in modern machine learning. Yet many geomet...

By Rahul Moorthy, Volkan Isler

diffusion benchmarks

arXiv Computer Vision

Oct 26

NS-Net: Decoupling CLIP Semantic Information through NULL-Space for Generalizable AI-Generated Image Detection

arXiv:2508.01248v5 Announce Type: replace Abstract: The rapid progress of generative models, such as GANs and diffusion models, has facilitated the creation of highly realistic images, raising growin...

By Jiazhen Yan, Fan Wang, Ziwen He, Ziqiang Li, Zhangjie Fu

diffusion benchmarks

arXiv Computer Vision

Oct 26

A Closer Look at Evaluation of Text-to-Video Models Under Camera Motion

arXiv:2510.07441v2 Announce Type: replace Abstract: Existing text-to-video (T2V) evaluation benchmarks, such as VBench and EvalCrafter, predominantly contain either subject-centric prompts or static...

By Nithin C. Babu, Aniruddha Mahapatra, Harsh Rangwani, Rajiv Soundararajan, Kuldeep Kulkarni

diffusion benchmarks

arXiv Computer Vision

Oct 26

GenTrack2: An Improved Hybrid Approach for Multi-Object Tracking

arXiv:2510.24410v5 Announce Type: replace Abstract: This paper proposes a visual multi-object tracking method that jointly employs stochastic and deterministic mechanisms to ensure identifier consist...

By Toan Van Nguyen, Rasmus G. K. Christiansen, Dirk Kraft, Leon Bodenhagen

benchmarks

arXiv Computer Vision

Oct 26

Rethinking Densification in Gaussian SLAM: A Stationary Sampling Perspective

arXiv:2601.00705v4 Announce Type: replace Abstract: Gaussian Splatting enables high-fidelity differentiable SLAM by representing scenes as anisotropic Gaussian primitives. Most systems rely on residu...

By Wei-Tse Cheng, Yen-Jen Chiou, Yuan-Fu Yang

efficiency benchmarks

arXiv Computer Vision

Oct 26

Seeing Through the Chain: Understanding and Mitigating Hallucinations in Multimodal Large Reasoning Models

arXiv:2602.03380v3 Announce Type: replace Abstract: While multimodal reasoning models (MLRMs) have exhibited impressive capabilities, they remain prone to hallucinations, and effective solutions are...

By Hao Fang, Jinyu Li, Jiawei Kong, Tianqu Zhuang, Kuofeng Gao, Bin Chen, Shu-Tao Xia

multimodal benchmarks safety

arXiv Computer Vision

Oct 26

DisPOSE: Projected Polystochastic Diffusion for Self-Supervised Multi-View 3D Human Pose Estimation

arXiv:2606.07419v4 Announce Type: replace Abstract: Recovering 3D human poses for multiple individuals from different camera views is a fundamental bottleneck for analyzing interacting behaviors. Exi...

By Tony Danjun Wang, Tolga Birdal, Nassir Navab, Lennart Bastian

diffusion computer-vision benchmarks

arXiv Computer Vision

Oct 26

Barycentric Guidance: Turning Foundation Image Editors into Continuous Affective Controllers

arXiv:2610.16892v2 Announce Type: replace Abstract: Emotions are expressed on a continuum and are naturally described in the valence-arousal (VA) space. Existing VA-based image editors are typically...

By Harvey Mannering, Zhiwu Huang, Adam Pr\"ugel-Bennett

fine-tuning benchmarks

arXiv Computer Vision

Oct 26

Velocity-Space 3D Asset Editing

arXiv:2605.07385v2 Announce Type: replace-cross Abstract: Local 3D asset editing requires modifying a target region while preserving the rest. Existing methods enforce locality through mechanisms ext...

By Hao Liu, Yuxuan Lin, Jingfeng Guo, Ruihang Chu, Junjie Wang, Ruotong Li, Yujiu Yang

rag benchmarks

Get the daily briefing