Under a fixed context budget, which objects and relations should a 3D scene-grounded VLM see first? On ScanNet indoor referring benchmarks (Dai et al., 2017), matching the query to object category names outperforms pairwise geometry scoring at every reported K. The gaps are largest at high recall. Analytic pairwise cues beat per-object cue scoring and query-agnostic kNN graphs, including on paraphrases. MiniLM and BGE-small still score higher on those splits. We evaluate token-budgeted candidate retrieval with axis-aligned boxes, a token-ratio metric, training-free baselines, two small encoders that match q to each object's category name, and QCRR (Query-Conditioned Relation Retrieval), a deterministic pairwise-geometry scorer. Across ScanRefer gt_val plus a custom 20% scan-id split of Nr3D and Sr3D (35,504 queries; not official ReferIt3D val), additive noun matching reaches R@10 0.864 on ScanRefer against QCRR's 0.626; MiniLM and BGE-small reach 0.911 to 0.913 on ScanRefer and 0.941 to 0.947 on Nr3D. A corrected 3DGraphLLM harness (native Acc@0.25 0.67 on the full graph, n=300 ScanRefer queries) shows that context selection changes downstream accuracy under a matched object budget (Random 0.44, QCRR 0.56, MiniLM 0.67, oracle 0.70). Semantic retrieval beats hand-designed geometry on that harness. We will release the protocol, retriever implementations, and per-query outputs so new selectors can be swapped in without rewriting the analysis.
Vision-language models (VLMs) such as CLIP have shown promising performance on a variety of recognition tasks using the standard zero-shot classification procedure -- computing similarity between the query image and the embedded words for each category. By only using the category name, they neglect to make use of the rich context of additional information that language affords. The procedure gives no intermediate understanding of why a category is chosen, and furthermore provides no mechanism for adjusting the criteria used towards this decision. We present an alternative framework for classif…
School of Computer Science and Technology, Soochow University（苏州大学计算机科学与技术学院）；Department of Computer Science, The Hong Kong Polytechnic University（香港理工大学计算机科学系）
Learning to Rank Pre-trained Vision-Language Models for Downstream Tasks
School of Computer Science and Technology, Anhui University（安徽大学计算机科学与技术学院）；School of Artificial Intelligence, Anhui University（安徽大学人工智能学院）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
National University of Singapore（新加坡国立大学）；University of Science and Technology of China（中国科学技术大学）
Large-scale vision-language models (VLMs) pre-trained on billion-level data have learned general visual representations and broad visual concepts. In principle, the well-learned knowledge structure of the VLMs should be inherited appropriately when being transferred to downstream tasks with limited data. However, most existing efficient transfer learning (ETL) approaches for VLMs either damage or are excessively biased towards the prior knowledge, e.g., prompt tuning (PT) discards the pre-trained text-based classifier and builds a new one while adapter-style tuning (AT) fully relies on the pre…
Teaching VLMs to Localize Specific Objects from In-context Examples
IBM Research（IBM研究院）；Weizmann Institute of Science（魏茨曼科学研究所）；Tel Aviv University（特拉维夫大学）；JKU Linz（林茨约翰内斯·开普勒大学）；Tuebingen AI Center（蒂宾根人工智能中心）；MIT-IBM（麻省理工学院-IBM联合机构）；MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）
Texture or Semantics? Vision-Language Models Get Lost in Font Recognition
University of California, San Diego（加州大学圣地亚哥分校）；ByteDance（字节跳动）；The University of Queensland（昆士兰大学）；University of Southern California（南加州大学）；University at Buffalo（布法罗大学）；University of California, Merced（加州大学默塞德分校）
Eagle 2: Building Post-Training Data Strategies from Scratch for Frontier Vision-Language Models
Nanjing University（南京大学）；Tsinghua University（清华大学）；Hong Kong Polytechnic University（香港理工大学）；Johns Hopkins University（约翰斯·霍普金斯大学）；New York University（纽约大学）；NVIDIA（英伟达）
Dual Distribution Estimation for Zero-shot Noisy Test-Time Adaptation with VLMs
The Hong Kong Polytechnic University（香港理工大学）；Eastern Institute of Technology, Ningbo（宁波东方理工大学）；Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））；Shanghai Jiao Tong University（上海交通大学）
Towards Joint Quantization and Token Pruning of Vision-Language Models
VCIP, College of Computer Science, Nankai University（VCIP，计算机科学学院，南开大学）；School of Computer Science and Engineering, Tianjin University of Technology（计算机科学与工程学院，天津工业大学）；OPPO Research Institute（OPPO研究院）；Academy for Advanced Interdisciplinary Studies, Nankai University（先进跨学科研究院，南开大学）；Nankai International Advanced Research Institute, Shenzhen Futian（南开国际先进研究 institutes，深圳福田）；Department of Computing, Hong Kong Polytechnic University（计算学院，香港理工大学）
Replace-then-Perturb: Targeted Adversarial Attacks With Visual Reasoning for Vision-Language Models
Institute of New Media and Communications, Seoul National University（首尔国立大学新媒体与通信研究所）；Pohang University of Science and Technology (POSTECH)（浦项科技大学）；Department of Electrical and Computer Engineering, Seoul National University（首尔国立大学电气与计算机工程系）
HoVLE: Unleashing the Power of Monolithic Vision-Language Models with Holistic Vision-Language Embedding
Tsinghua University（清华大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；The Chinese University of Hong Kong（香港中文大学）；Johns Hopkins University（约翰斯·霍普金斯大学）；SenseTime Research（商汤科技研究院）；Nanjing University（南京大学）
SSR: Enhancing Depth Perception in Vision-Language Models via Rationale-Guided Spatial Reasoning
Westlake University（西湖大学）；Zhejiang University（浙江大学）；Harbin Institute of Technology（哈尔滨工业大学）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Shanghai Innovation Institute（上海创新研究院）
