Benchmarks and evaluation

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

28,322 stories · RSS feed

arXiv Computer Vision

Sep 22

LINGO: Latent Initialization and Gradient Optimization for Sparse-view X-ray Novel View Synthesis and CT Reconstruction with 3D Gaussian Splatting

arXiv:2609.22849v1 Announce Type: new Abstract: In novel view synthesis and Computed Tomography (CT) reconstruction with sparse-view X-ray imaging, insufficient angular coverage leads to structural a...

By Lifeng Xing, Dequan Jin, Kunpeng Bu, Peigeng He, Shihui Ying

benchmarks

arXiv Computer Vision

Sep 22

Planning and Rendering in Concert: DeepFusion of Autoregressive Layouts and Diffusion for Visual Text Generation

arXiv:2609.22916v1 Announce Type: new Abstract: Generating text-rich images from prompts requires both textual fidelity and the coherent integration of text into the surrounding image. An explicit la...

By Guanqiao Chen, Jingru Tan, Dongxing Mao, Catherine Chen, Zijian Du, Libo Qin, Hu Jian Guo, Alex Jinpeng Wang

llms agents diffusion benchmarks

arXiv Computer Vision

Sep 22

Compressing 3D Gaussian Splatting via Cross-Representation Priors

arXiv:2609.23005v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) enables high-quality novel view synthesis but incurs high storage and transmission costs due to dense Gaussian primitives....

By Yezheng Zhang, Huanxiong Liang, Chuqin Zhou, Guo Lu, Wenjun Zhang

benchmarks

arXiv Computer Vision

Sep 22

LD-RSVIS: A Large-Scale and Diverse Benchmark for Referring Surgical Video Instrument Segmentation

arXiv:2609.23067v1 Announce Type: new Abstract: Referring surgical video instrument segmentation (RSVIS) aims at segmenting the instrument in a surgical video, given a textual description. Despite re...

By Zan Wang, Yunhe Feng, Dong Nie, Oluwatosin Oluwadare, Kewei Sha, Yan Huang, Heng Fan

computer-vision benchmarks

arXiv Computer Vision

Sep 22

RegVGGT: Sustainable Visual Geometry Grounding for Streaming via Regulated Memory

arXiv:2609.23286v1 Announce Type: new Abstract: 3D reconstruction from a lengthy video stream input poses a dilemma for feed-forward reconstruction models (FFRMs), that a whole-stream inference conte...

By Hongbo Mao (Harbin Institute of Technology), Junjun Jiang (Harbin Institute of Technology), Youyu Chen (Harbin Institute of Technology), Jiaxin Zhang (Harbin Institute of Technology), Zhemeng Dong (Harbin Institute of Technology), Xianming Liu (Harbin Institute of Technology)

benchmarks

arXiv Computer Vision

Sep 22

ScaleBlind: Point Cloud Completion under Unknown Scale

arXiv:2609.23404v1 Announce Type: new Abstract: Point cloud completion aims to infer a complete 3D shape from a partial point cloud and serves as a fundamental building block for downstream tasks suc...

By Shenghui Wu, Chen Wang, Yuan Feng, Guangshun Wei, Yuanfeng Zhou, Changjian Li

diffusion multimodal benchmarks

arXiv Computer Vision

Sep 22

GeoBalance: Geometry-Aware Monitoring and Reconstruction with Asymmetric Optimization for Balanced Multimodal Learning

arXiv:2609.23533v1 Announce Type: new Abstract: Multimodal classifiers can converge to modality-dominant solutions in which one modality dominates the joint prediction, suppressing the learning of ot...

By Zechang Xiong, Da Li, Rong Yin, Kexin Tang, Biao Yang, Pengyuan Li, Wenkang Kong, Yulan Hu, Shengyu Zhu, Hao Peng

multimodal benchmarks

arXiv Computer Vision

Sep 22

PosEviLoc: Position-Conditioned Spatial Evidence for Language-Based 3D Localization

arXiv:2609.23534v1 Announce Type: new Abstract: Language-based 3D localization retrieves the point-cloud submap containing a target position from descriptions of nearby objects and their spatial rela...

By Tianyi Shang, Yike Shi, Zhenyu Li

efficiency benchmarks

arXiv Computer Vision

Sep 22

SewFusion: Tailored Generation of Topology and Panel-Level Geometry for Sewing Patterns

arXiv:2609.23548v1 Announce Type: new Abstract: Generating sewing patterns from images and text requires modeling a heterogeneous representation composed of discrete topology and continuous geometry....

By Jiaxin Lin, Xiao Pan, Hangjie Yuan, Luyan Liang, Wan Li, Daquan Feng

diffusion multimodal benchmarks

arXiv Computer Vision

Sep 22

Beyond UV Mapping: Mesh Texture Compression via Surface-Aligned Texture Fields

arXiv:2609.23606v1 Announce Type: new Abstract: Mesh texture compression typically relies on 2D UV atlases, whose chart discontinuities and mapping overhead can limit coding efficiency. To tackle thi...

By Jianqiang Wang, Junhui Hou, Siyu Ren, Weiyao Lin, Wenping Wang

efficiency benchmarks

arXiv Computer Vision

Sep 22

Layer-Aware Position Embeddings for Visual Token Pruning in Multimodal Large Language Models

arXiv:2609.23715v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) incur substantial computational overhead due to the reliance on hundreds of visual tokens to represent images....

By Yahong Wang, Zhangkai Ni, Juncheng Wu, Yuyin Zhou, Ying Wen, Lianghua He

llms rag efficiency multimodal benchmarks

arXiv Computer Vision

Sep 22

Confidence-Aware Teacher-Student Distillation for 3D Medical Segmentation

arXiv:2609.23815v1 Announce Type: new Abstract: Medical image segmentation models typically rely on large amounts of densely annotated volumetric data, limiting their scalability across tasks and ima...

By Georgios Triantafyllou, Dimitris K. Iakovidis

computer-vision efficiency benchmarks

arXiv Computer Vision

Sep 22

Positive Pair Geometry Matters: Optimal Transport for Contrastive Learning of Visual Representations

arXiv:2609.24125v1 Announce Type: new Abstract: Contrastive self-supervised learning has achieved strong performance by learning representations from multiple augmented views of the same image. Howev...

By Akshit Nanda, Shahzad Ahmad, Ram Prasad Padhy

fine-tuning benchmarks

arXiv Computer Vision

Sep 22

LegendBench: A Diagnostic Benchmark for Legend Understanding with Counterfactual Interventions

arXiv:2609.24172v1 Announce Type: new Abstract: Legends are fundamental to chart understanding, as reliable interpretation requires correctly binding legend entries to corresponding visual marks. Whi...

By Xinnuo Zhang, Zhike Tang, Jing Xu, Haoyuan Zhao, Weikai Yang

llms fine-tuning multimodal benchmarks

arXiv Computer Vision

Sep 22

ChartJudgeBench: Evaluating LMM Judges for Chart-to-Code Generation

arXiv:2609.24210v1 Announce Type: new Abstract: Building strong chart-to-code systems increasingly relies on reinforcement learning, whose effectiveness depends critically on the quality of the rewar...

By Lijian Wu, Henry Hengyuan Zhao, Zijian Zhang, Jiahao Tang, Jiajun Wu, Alex Jinpeng Wang

agents reinforcement-learning multimodal benchmarks safety

arXiv Computer Vision

Sep 22

Document Retrieval-Aware Chunking (D-RAC): Universal Retrieval-Aware Ingestion of Enterprise Documents via PDF Normalization and Multimodal Markdown Conversion

arXiv:2609.24220v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) systems over enterprise knowledge bases must ingest heterogeneous document formats -- PDFs, Word documents, presen...

By Uday Allu (AI Research Team Yellow.ai), Abhivanth Sivaprakash (AI Research Team Yellow.ai), Pratik Singh (AI Research Team Yellow.ai), Aman Manocha (AI Research Team Yellow.ai)

llms rag agents computer-vision multimodal benchmarks safety

arXiv Computer Vision

Sep 22

Hierarchical Prompt Learning for Hyperbolic Vision-Language Models

arXiv:2609.24276v1 Announce Type: new Abstract: Hyperbolic vision-language models (VLMs) represent image and text features in a geometry naturally suited to hierarchy, but their adaptation to downstr...

By Andro Erdelez, Pascal Mettes, Behzad Bozorgtabar

llms rag multimodal benchmarks

arXiv Computer Vision

Sep 22

Dynamic Thermal Gaussians: Multimodal 4D Gaussian Splatting

arXiv:2609.24531v1 Announce Type: new Abstract: Thermography plays a vital role in military and broader thermal analysis applications. Recent progress in 3D thermal reconstruction has extended temper...

By Rongfeng Lu, Lifeng Lin, Xiaobao Wei, Quan Chen, Ming Lu, Yitian Xue, Yaoqi Sun, Yuhan Gao, Anke Xue, Chenggang Yan

rag multimodal benchmarks

arXiv Computer Vision

Sep 22

ReSTI: A Source-Grounded Audit and Repair of STI-Bench

arXiv:2609.24727v1 Announce Type: new Abstract: Spatial--temporal benchmarks are valid only when their questions, source annotations, and answer options identify the same physical quantity. We audit...

By Pengzhan Sun, Ramanathan Rajaraman, Shiu-Hong Kao, Junbin Xiao, Angela Yao

benchmarks safety

arXiv Computer Vision

Sep 22

Toward a foundation model for forest point clouds

arXiv:2609.24787v1 Announce Type: new Abstract: Forest inventories increasingly rely on artificial intelligence (AI) models to derive forest attributes from large-scale 3D point clouds. Current model...

By Yuanwen Yue, Stefano Puliti, Damien Robert, Atakan Topalo\u{g}lu, Binbin Xiang, Maciej Wielgosz, Jan Dirk Wegner, Rasmus Astrup, Christian Rupprecht, Konrad Schindler

computer-vision benchmarks

Get the daily briefing