The paper describes the CERTH-ITI team’s approach to the TRECVID 2025 Ad-hoc Video Search (AVS) and Video Question Answering (VQA) tracks. For AVS, a two-stage framework uses foundation vision‑language models for initial retrieval and a Multimodal‑LLM for reranking, improving contextual matching without training. In VQA, an audio‑visual MLLM is fine‑tuned and enhanced with inference‑time scaling; answer generation employs majority voting over responses from random frame subsets, while multiple‑choice responses use mean‑pooling logits, yielding top performance on VQA metrics.
By Andreas Goulas, Damianos Galanopoulos, Ioannis Patras, Vasileios Mezaris
TAN (Tissue‑Aware Network) is a lightweight convolutional encoder that processes tissue‑conforming superpixels in their native shape, avoiding background leakage from padding or masking. It achieves accuracy on the BACH histology dataset comparable to a 303‑million‑parameter foundation model while using only 0.41 M parameters and 1,190× fewer FLOPs, and its embeddings are invariant to the choice of fill value. On the BRACS dataset, TAN performs close to a ResNet18 trained under the same protocol and outperforms standard masked‑crop processing with less than half the computational cost.
By Jan Herschel, Anselm von Gladiss
The paper introduces GazeCLIP, a gaze‑guided CLIP framework that uses adaptive‑enhanced fine‑grained language prompts for deepfake attribution and detection (DFAD). It presents a new benchmark evaluating DFAD on novel generative methods such as diffusion and flow models, and proposes a gaze‑aware image encoder (GIE) that fuses gaze prompts with image embeddings to capture global forgery patterns. A language refinement encoder (LRE) further refines language embeddings for precise vision‑language matching, achieving state‑of‑the‑art performance with 6.56% higher accuracy and 5.32% higher AUC on the benchmark.
By Yaning Zhang, Linlin Shen, Zitong Yu, Chunjie Ma, Zan Gao
The paper introduces PRISm, an image-to-image retrieval framework that prioritizes important elements in scene graphs for semantic image search. PRISm uses an Importance Prediction Module, trained with caption-derived relevance, to prune irrelevant objects and relations, and an Edge-Aware Contextual GNN to fuse the refined graph with global visual features into a single embedding. Experiments on PSG and Flickr show that PRISm outperforms strong baselines in MAP@1 and top‑1 metrics while adding only 33 ms per query beyond scene‑graph generation.
By Dimitrios Georgoulopoulos, Nikolaos Chaidos, Angeliki Dimitriou, Giorgos Stamou
EKLAV is a method that uses a teacher’s chain‑of‑thought (CoT) reasoning as privileged input while supervising only the final answer. By strategically placing parts of the trace in the prompt, EKLAV improves ranking performance on BRIGHT passage reranking and table‑reranking benchmarks, outperforming full‑trace distillation and answer‑only training. The approach reduces training compute and inference time, and the generated traces show more efficient reasoning patterns.
By Adarsh Singh, Aman Singh, Kushal Raj Bhandari, Soham Dan, Anoop Kumar, Vivek Gupta
arXiv:2610.22749v1 Announce Type: new
Abstract: Do larger models learn increasingly similar representations of the same world? The Platonic Representation Hypothesis (PRH) predicts that they should,...
By Angus Hoy, Austin Lutterbach, Jasper Chong, Aman Kumar, Michael J. Smith
arXiv:2610.23404v1 Announce Type: new
Abstract: Information-theoretic measures, such as Mutual Information (MI), play a crucial role in understanding non-linear relationships between random variables...
By Alberto Foresti, Giulio Franzese, Pietro Michiardi
arXiv:2610.23455v1 Announce Type: cross
Abstract: LLMs and LVLMs are increasingly deployed across heterogeneous hardware, ranging from data-center GPUs to resource-constrained edge devices. Their fix...
By Oscar Kemme, Janek Haberer, Ali Hojjat, Olaf Landsiedel
arXiv:2602.04926v2 Announce Type: replace-cross
Abstract: Retrieval-augmented generation (RAG) has become a standard approach for knowledge-intensive LLM tasks. Complex reasoning remains challenging...
By Ning Wang, Kuanyan Zhu, Daniel Yuehwoon Yee, Yitang Gao, Shiying Huang, Zirun Xu, Sainyam Galhotra
arXiv:2610.22652v1 Announce Type: new
Abstract: Consumers often describe what they need rather than use the terminology found on a banking website. For example, a natural-language request ("a card fo...
By Ahmed Mohamed Mahmoud Rayyan, Rana Mahmoud Mohammed, Aya Abdallah Abdelmonem, Mohamed Khaled Goda Othman, Rahatara Ferdousi
arXiv:2610.22796v1 Announce Type: new
Abstract: Reusing a Transformer block across depth increases computation without replicating its parameters, but successive passes have no dedicated state throug...
By Ilia Zaznov
arXiv:2610.22720v1 Announce Type: new
Abstract: High-fidelity 3D generative modeling underpins game asset creation, medical imaging, and VR/AR environmental design, where geometric structure directly...
By Ziyi Zhang, Shixuan Li, Yorie Nakahira, Paul Bogdan, Guannan Qu
arXiv:2610.23416v1 Announce Type: new
Abstract: Multimodal Large Language Models (MLLMs) have significantly advanced instruction-driven perception through the "Embedding-as-Mask" paradigm. However, e...
By Cheng Fan, Han Wu, Tingzhang Luo, Minjing Dong, Yehui Tang, Jianyuan Guo
arXiv:2605.03857v2 Announce Type: replace
Abstract: This work presents a deeper analysis of the "irreversibility" property of PolyProtect, a biometric template protection method initially proposed fo...
By Vedrana Krivoku\'ca Hahn, J\'er\'emy Maceiras, S\'ebastien Marcel
The study investigates how information about words and passage context is represented across the layers of the Llama‑3.1‑8B language model during silent reading, using EEG recordings. Decoders trained on each layer show that word‑level decodability peaks in early layers and diminishes toward the final layer, while a context‑tracking component increases with depth. Even a single 0.5‑second EEG window can capture passage‑level information, and control experiments confirm that this context tracking is driven by the text rather than by word decoding or session artifacts.
By Ingo Marquardt, Anthilia Alchanat, Priyanka Jain
The paper introduces a model‑agnostic framework that lets frozen large language models (LLMs) and vision‑language models (VLMs) learn from deployment experience without retraining. It does so by adding three external expertise components—a Skill for guiding reasoning and tool use, a Knowledge Memory for storing reliable facts, and a Multimodal Knowledge Base for visual examples—and by using a validation strategy that updates only when new cases improve performance without harming past performance. Experiments on six benchmarks with both open‑weight and closed‑source models show up to a 34.2% performance gain on medical tasks, generalization to unseen cases, and transferability to other models and non‑medical domains.
By Yexiao He, Yucheng Tang, Pengfei Guo, Yufan He, Andriy Myronenko, Can Zhao, Ang Li, Daguang Xu, Dong Yang
arXiv:2610.23618v1 Announce Type: new
Abstract: Staging a theatre performance requires coordinating dialogue, actor movement, stage directions, lighting focus, cue timing, and equipment constraints w...
By Md. Mehedi Hasan Naeem, Mst. Kamrunnahar Ruma, Shakila Sultana, Nafiza Anjum, Nasreen Jannatun Nemu, Md. Sujan Ali
arXiv:2610.22797v1 Announce Type: cross
Abstract: Reasoning rerankers write a rationale before ranking a candidate slate, and existing systems read item metadata to do so, even though generative reco...
By Zhenwei Tang, Jintao Liu, Di Bai, Xidong Wu, Xinwu Cheng
arXiv:2610.23807v1 Announce Type: new
Abstract: While deriving text embeddings directly from frozen LLMs has emerged as a promising direction, existing methods focus almost exclusively on English, le...
By Ailiang Lin, Zhuoyun Li, Yusong Wang, Keyu Mao, Kotaro Funakoshi, Manabu Okumura
arXiv:2610.23588v1 Announce Type: cross
Abstract: Medical Vision-Language Models (Med-LVLMs) have shown strong performance in Medical Visual Question Answering (MVQA), yet they may still produce fact...
By Daniela Jimenez-Pano, Hugo Jair Escalante, Delia Iraz\'u Hern\'andez-Far\'ias