The paper investigates how the choice of retrieval encoder affects cache‑based test‑time adaptation for CLIP. By keeping the memory fixed and varying the retrieval space across sixteen encoders, the authors show that retrieval space can dramatically alter performance, with gains ranging from +0.44 to +19.7 points on ImageNet‑A. They introduce MARC, a training‑free system that pairs frozen CLIP with DINOv2‑B for retrieval, achieving superior out‑of‑distribution accuracy and efficiency compared to prior methods.
By Mahir Shahriar Tamim, Md. Samiul Alim, Azmine Toushik Wasi, Shahriyar Zaman Ridoy, Meharun Nesa, Mohammad Abu Yousuf, Alex Lamb, Mohammad Ali Moni
Frozen visual foundation models provide transferable features for visual place recognition, but fixed aggregation can suppress useful distinctions in new environments. We introduce TFA, a reliability-...
The paper introduces TFA, a training‑free aggregation technique that calibrates frozen visual foundation models for visual place recognition. TFA uses cross‑codebook agreement, retrieval coverage, and spectral statistics to adjust residual assignment, spectral shaping, and global‑feature fusion without requiring place labels or task‑specific weights. Experiments with a DINOv2‑B backbone show significant Recall@1 gains over existing training‑free methods across multiple benchmarks, demonstrating that reliability‑guided aggregation can unlock additional retrieval performance from frozen representations.
By Xin Li, Zhimin Mao, Shang Wang, Siyuan Duan, Geng Zhang
arXiv:2606. 01790v1 Announce Type: cross Abstract: Vision-language-model-based graphical user interface (GUI) agents have shown broad automation capabilities, yet deployment is bottlenecked by a key-value (KV) cache that grows linearly with interaction steps.
By Yuhang Han, Wenzheng Yang, Yujie Chen, Xiangqi Jin, Yaojie Zhang, Siteng Huang, Linfeng Zhang
arXiv:2608. 13144v1 Announce Type: cross Abstract: As edge-side vision services continue to expand toward low-latency, high-throughput scenarios, reducing the inference cost of vision models without sacrificing reliability has become a central concern.
By Zhengzhe Xiang, Yinlin Chen, Fuli Ying, Binbin Zhou, Hailiang Zhao, Schahram Dustdar
arXiv:2605.25333v3 Announce Type: replace
Abstract: Video world models should maintain evolving states when evidence is unobserved, yet current generators often freeze hidden states upon interruption...
By Tianshuo Xu, Yichen Xie, Depu Meng, Chensheng Peng, Quentin Herau, Bo Jiang, Yihan Hu, Wei Zhan
ReVisIT is a train‑free framework that turns retrieved image‑label pairs into units of visual thought, combining structured class definitions, multimodal retrieval, and alternating user/assistant injection before joint decoding. On several benchmarks—including Fast Open MiniImageNet, Bongard‑OpenWorld, and the newly released MAAC‑Bench—ReVisIT achieves performance comparable to or surpassing large, trained models while using far fewer parameters. The approach demonstrates that high‑quality retrieval and a simple turns layer can provide a universal performance boost across diverse multimodal tasks.
By Bingchen Huang, Zhiling Wang, Yifu Chen, Yuanchao Du
arXiv:2607. 18885v1 Announce Type: new Abstract: Kernel-based alignment of CLIP toward a vision centric teacher such as DINOv2 (KUEA) improves CLIP's visual representations while preserving text-encoder compatibility, using a fixed trade-off weight tuned on curated ImageNet-1K.
By Micha{\l} Paw{\l}owicz
arXiv:2609.39096v1 Announce Type: new
Abstract: Autoregressive video diffusion supports streaming generation and interactive control, but its KV cache grows with the generated history. Existing compr...
By Zeqi Xiao, Qingle Liu, Kaiwen Zhang, Yifan Zhou, Zihan Ding, Xingang Pan
VisCache introduces a two-stage, plug‑and‑play framework for pruning visual key‑value caches in Vision Large Language Models without retraining. The first stage filters out temporally redundant keyframes, while the second stage, PruneKV, applies a parabolic layer‑wise budget and asymmetric update to selectively prune keys and fuse values, preserving essential context. Experiments show up to 2.35× speedup and significant memory savings with only 19–28% of the original cache retained, outperforming existing baselines.
By Lyuke Wang, Zhuo Li, Guangxu Zhu
MINER is a training‑free inference framework that enhances frozen dual‑encoder models for text‑to‑image retrieval when queries refer to small, visually subordinate objects in cluttered scenes. It augments the global image embedding with a bank of region‑level embeddings and applies hubness‑correcting similarity rescoring, thereby recovering visual evidence that global pooling underweights. The authors introduce ROCS, a benchmark derived from Flickr30K and MS COCO, and demonstrate that MINER improves retrieval performance across CLIP, SigLIP, and SigLIP 2 backbones on both ROCS and standard splits, attributing gains mainly to broader spatial coverage rather than precise crop placement.
By Abdulmalik Alquwayfili, Faisal AlMeshal, Jumanah Almajnouni, Huda Abdulhadi Alamri, Muhammad Kamran J Khan
The study investigates how long‑video language models decide which frames to keep, compress, and reuse, testing each decision in isolation across six selection rules, three benchmarks, and two answering models. It finds that selecting frames based on queries yields the biggest performance boost, that halving spatial resolution costs little, and that reallocating saved tokens to more compressed frames can further improve accuracy. The work also highlights the importance of a unified evaluation harness to avoid misleading comparisons.
By Prakhar Khatri