The paper demonstrates that sharing a deep encoder alone does not eliminate the confounding effects in task-comparison scores. By introducing a conditional two‑discriminator discrepancy within the embedding space, the authors achieve robust detection of task changes, maintaining stability under input rotations and accurately tracking label‑permutation drift. This approach, integrated into a mixture‑of‑heads framework, outperforms traditional novelty triggers and generalizes across multiple backbones and datasets, including ImageNet‑21k ViT‑B/16, DINOv2, and CIFAR‑100.
By Kentaro Oda
arXiv:2606. 27242v1 Announce Type: new Abstract: Training-free source selection for LLM families with shared vocabularies arises in scientific string domains such as SMILES, protein, and genomic sequences, where candidate corpora share a tokenizer but differ in prediction targets.
By John Sweeney
The paper uncovers a systematic mismatch in modern text embeddings: while sentiment can be extracted with high accuracy from frozen encoders, the embeddings’ cosine similarity metric barely reflects polarity differences. Across eleven models from 2021–2026, a linear probe achieves up to 91.3% accuracy, yet cosine similarity margins are only 0.003–0.064, leading to poor retrieval performance (e.g., Qwen3-Embedding-4B’s 64.3 MAP). Introducing a lightweight supervised‑contrastive head (Sentiment‑Injected Sentence Embeddings) dramatically improves probe accuracy, retrieval MAP, and polarity margins, but at the cost of downstream semantic similarity.
"whyItMatters":"The findings reveal that widely used retrieval and clustering systems may ignore valuable sentiment information encoded in embeddings, impacting their effectiveness."
By Mahdi Naser Moghadasi
arXiv:2607.09086v2 Announce Type: replace
Abstract: We present Subtoken Vision Transformer (SubViT), a selective image tokenization method for fine-grained visual recognition. Standard Vision Transfo...
By Jie Zhu, Ivy Zhang, Minchul Kim, Xiaoming Liu
arXiv:2610.34610v1 Announce Type: new
Abstract: Vision-language anomaly detectors describe normal and abnormal appearance with text, and their gains are commonly credited to the semantic content of t...
By Arda Baris Basaran, Mesut Ceylan, Elgar Fleisch, Filipe Barata
arXiv:2609.10224v1 Announce Type: new
Abstract: Vision-language models such as CLIP embed images and text in a shared space, where modality-specific distributions often remain separated. Existing acc...
By Zonglin Yang, Huilan Ma, Xudan Zheng, Yuejun Xie
The paper introduces a controlled evaluation framework to determine when encoder adaptation is beneficial after correcting for class imbalance in long‑tailed recognition tasks. By separating unique support from representation allocation and comparing classifier‑only versus full‑network continuations, the study shows that encoder updates become worthwhile only when representation allocation is highly imbalanced, a transition that persists across various corrections and scales to ImageNet. The framework uses stage‑specific controls, multiple objectives, whole‑distribution metrics, and hierarchical inference to robustly estimate incremental encoder value.
By Zexing Zhang, Jichao Li, Tianyang Lei, Yiyin Zhang, Kewei Yang
arXiv:2607.01630v2 Announce Type: replace
Abstract: Dynamic expansion methods for class-incremental learning (CIL) protect task-specific knowledge by growing dedicated tokens or subnetworks, yet our...
By Bingchen Huang, Yifu Chen, Zhiling Wang, Yuanchao Du
We describe the DS@GT submissions to the ImageCLEFmedical Caption 2026 challenge, which continues a long-running benchmark on the ROCOv2 dataset with two tracks: Concept Detection (Task 1), assigning UMLS Concept Unique Identifiers (CUIs) to radiology images, and Caption Prediction (Task 2), generating natural-language captions. For Task 1, our primary submission was a three-way late-fusion ensemble of ConvNeXt-V2, BiomedCLIP ViT-B/16, and DenseNet-169 with a regularized ''Honest Threshold Tuning'' procedure designed to avoid validation overfitting on rare concepts; this submission ranked first on the official submission with a primary $F_1$ of $0.
arXiv:2609.37685v1 Announce Type: new
Abstract: Language-aligned and self-supervised visual encoders offer complementary strengths in semantic abstraction and spatial detail. Harnessing this compleme...
By Pinze Ren, Yuwei Zhang, Hao Chen, Linghao Meng, Chang Li, Qiankun Li
arXiv:2605.31192v2 Announce Type: replace
Abstract: Generalizable deepfake detection requires complementary forensic and semantic visual evidence. Specialist encoders capture subtle manipulation trac...
By Benedikt Hopf, Zongwei Wu, Radu Timofte
The paper introduces DARTS, a method for tuning decoder representations during model merging. It addresses representation bias in autoregressive decoders by using an entropy‑weighted L1 loss and a per‑position additive bias to correct errors that accumulate across token positions. Experiments on code generation, mathematical reasoning, and instruction following with Llama‑2‑7B show that DARTS improves performance over standard surgery while adding only 0.1% extra parameters.
By Aaryan Ajay Sharma, Sai Nishanth Padala, Seganrasan Subramanian