FLAT (Flexible‑Length Aligned Transmodal representations) is a joint multimodal pre‑training framework that learns a shared encoder for images and text, producing 1‑D continuous embeddings that can be directly used by downstream generative decoders. By combining contrastive alignment with bidirectional cross‑modal generative objectives, FLAT yields representations that are both discriminative and generative, enabling cross‑modal retrieval and generation with a single pre‑training stage. The model achieves strong performance on T2I generation (GenEval 71.1), image captioning (BLEU‑4 40.5, CIDEr 138.6), and retrieval tasks (Recall@5 86.8/75.8 on MS‑COCO, 98.3/93.6 on Flickr30K), and supports linear interpolation, latent space arithmetic, and zero‑shot composed retrieval.
By Guangyu Sun, Shlok Kumar Mishra, Wentao Bao, Robert Zhenheng Yang, Xiao Wang, Xiyuan Wang, Yujunrong Ma, Chen Yuan, Max Xiangjun Fan, Jun Xiao, Jianpeng Cheng
The paper proposes a method called language orthogonalization to improve zero‑shot cross‑lingual audio deepfake detection. By removing language‑dependent variation from self‑supervised speech models using a target‑free ridge map on language‑identification embeddings, the approach consistently lowers equal error rates across six languages and six model backbones. The gains are larger when the target language is more distant in the language‑identification space.
By Minu Kim, Ji Sub Um, Hoirin Kim
The paper introduces a framework that uses Large Language Models (LLMs) to generate synthetic time‑series data for manufacturing processes. By fine‑tuning pre‑trained LLMs on manufacturing instructions and applying Retrieval Augmented Generation (RAG), the method enhances data diversity and realism. Evaluation against traditional models such as ARIMA and LSTMs shows that the LLM‑driven approach produces higher‑quality synthetic data, better capturing temporal dependencies and improving downstream anomaly detection performance.
By Mantek Singh, Jeshwanth Challagundla, Prateek Karnal, Gagan Ganapathy, Vineet Shah, Ridam Arora
The paper argues that while machine-readable models like SysML v2 enable AI participation in systems engineering, the data architecture surrounding these models must also be robust. It introduces the concept of epistemic adequacy, split into read‑side adequacy (ensuring derivations, status, and provenance are answerable) and write‑side admissibility (filtering AI contributions before they enter the record). The authors illustrate their ideas using the public Apollo 11 SysML v2 reconstruction and propose a Governed‑Query Architecture Framework to enforce these principles.
By Jason Gower, Michael J. de C. Henshaw, Siyuan Ji
The paper introduces ORDER, a task‑conditioned retrieval‑augmented generation framework that dynamically adapts both indexing and retrieval strategies to each incoming query. It first clusters questions to learn cluster‑specific chunking, metadata filtering, and reranking settings, then routes queries to the appropriate pre‑built index via nearest‑centroid assignment. Additionally, a supervised query router predicts relevant collections and a Uniform Multi‑source Sampler distributes the retrieval budget evenly across selected sources, yielding superior performance on heterogeneous historical archives compared to existing RAG systems.
By Aur\'elien Pellet (LRE), Julien Perez, Marie Puren
The paper introduces a schema‑adaptive action‑conditioned Joint‑Embedding Predictive Architecture (SAAC‑JEPA) for cross‑machine CNC transfer when only a subset of sensors overlap between source and target machines. Experiments show that pretraining does not improve source‑only forecasting, but a carefully selected action‑conditioned JEPA model achieves a zero‑shot RMSE of 0.546 on the target, outperforming persistence but falling short of certain baseline models. Ablation studies reveal that adding RevIN improves RMSE but harms calibration, and limited post‑lock adaptation can further reduce error.
By Ayoub Louaye Bouaziz, Matthieu Ostertag, Anton Demasles
RegRet is a large multimodal model framework that improves region-level retrieval by adding a Region‑Aware Encoder and a multi‑stage training pipeline featuring localized captioning and regional contrastive learning. It also introduces the REGMB benchmark, containing 225k contrastive pairs across four multimodal retrieval tasks. Experiments show RegRet surpasses strong baselines in zero‑shot settings and gains over 20% improvement on REGMB and public benchmarks while maintaining global retrieval performance.
By Xun Liang, Honghui Yang, Weihang Pan, Ruisi Zhao, Boyuan Pan, Yao Hu, Wenxiao Wang, Binbin Lin, Deng Cai
The paper re‑examines the impact of removing the encoder from Action Chunking Transformers (ACT), a model used for robot manipulation learning. Contrary to the original claim that encoder removal drops success rates from 35% to 2%, the authors find no such dramatic effect in their re‑runs, though minor variations remain uncertain. They attribute discrepancies to training length and checkpoint selection, and note that the encoder’s latent variable offers little reconstruction benefit on the tested benchmark, while its removal speeds up training.
By Bo Kang
The paper investigates intersectional biases in multimodal clinical predictions using Electronic Healthcare Records (EHR). It introduces datasets MIMIC-Eye1 and MIMIC-IV ED, applies unified text representations from pre‑trained clinical language models, and benchmarks bias mitigation at the intersectional subgroup level. Results show that subgroup‑specific mitigation is robust across datasets, subgroups, and embeddings, effectively addressing intersectional biases in multimodal settings.
By Ayaazuddin Mohammad, Kishore Sampath, Resmi Ramachandranpillai
arXiv:2609.16179v1 Announce Type: new
Abstract: Z-loss has been widely applied to the logits of language-model output heads and sparse mixture-of-experts routers. Z-loss constrains the softmax log-no...
By Bum Jun Kim
arXiv:2609.17509v1 Announce Type: cross
Abstract: Neural audio codecs are a key component in speech language modeling. However, their high frame rates lead to long sequence lengths, increasing comput...
By Thanapat Trachu, Samuele Cornell, William Chen, Shinji Watanabe
arXiv:2609.16603v1 Announce Type: new
Abstract: Full-context neural visual geometry is impractical for thousands of images, while sequence-based chunking poorly captures irregular non-local overlap i...
By Jeng Wen Joshua Lean, Ting-Yu Yen, Wei-Fang Sun, Simon See, Hung-Kuo Chu, Shih-Hsuan Hung
Lit3R is a system developed by tus-nlp for the LitTraceQA shared task, which focuses on evidence-grounded question answering over scientific literature. The system combines off-the-shelf retrieval, reranking, and large language model components without task-specific training, using an iterative retrieval process that merges BM25-based sparse and dense retrieval, cross-encoder reranking, and LLM verification, along with paper-to-paper expansion. In the official test set, Lit3R achieved a 4th place ranking on the leaderboard.
By Akira Ise, Kotaro Kumagai, Yuta Yamaguchi, Hisanori Ozaki, Yukio Uematsu, Ikuya Yamada
EviScope is a new paired counterfactual benchmark that evaluates grounded language models by fixing the question while manipulating evidence—adding, removing, distracting, or contradicting it. The v1.1 dataset includes 40 four‑condition quartets with repaired counterfactual claims and span‑level support labels for automated assessment. Experiments on Qwen2.5‑7B, Llama 3.1 8B, and Gemini 3.5 Flash show that paired metrics reveal grounding behaviors hidden by simple answer accuracy, such as unsupported answers, conflict blindness, and incorrect non‑answer actions.
By Suryadeep Singh Deswal
DenseFace introduces a bias‑mitigation technique for face recognition that operates on pre‑trained models without retraining. It models each person’s face embeddings with a von Mises‑Fisher distribution and uses a density‑aware probabilistic matching procedure to account for demographic differences. Experiments show that DenseFace consistently reduces racial bias across various architectures and datasets while preserving recognition accuracy.
By Mansur Bultygov, Vadim Seliutin, Dmitry Nekhaev, Ivan Laptev
The paper introduces LSREP, a Longitudinal State‑Replay Evaluation Protocol designed to assess how conversational memory evolves over time, incorporating ordered replay, lifecycle schedules, repeated probes, evolving reference answers, and mechanism‑fidelity checks. It applies LSREP to ICE v2, a local‑first memory middleware, and reports that on three ordinary‑density datasets ICE v2 achieves near‑zero mean quality difference from vector‑RAG while using fewer fragments but slightly more prompt tokens, yet fails catastrophically on a dense dataset. In a public diagnostic, ICE v2 underperforms pure vector‑RAG on LongMemEval, revealing significant multi‑session and temporal failures and a quality‑cost trade‑off rather than superior efficiency.
By Deepesh Sonar
EMODY Flow is a lightweight flow‑matching framework that generates synchronized full‑body motion and facial expressions conditioned on speech and emotion. It attaches to a frozen Qwen‑3 Omni model, reusing its audio codecs to drive two parallel DiT generators for SMPL‑X body pose and FLAME facial expressions. An auxiliary emotion classifier at training time restores emotion sensitivity, enabling EMODY Flow to achieve state‑of‑the‑art gesture quality on BEAT2 and zero‑shot facial animation on TFHP, with significant improvements in FGD, Beat Correlation, and Diversity metrics.
By Harsh Kumar Agarwal, Xavier Alameda-Pineda, Olivier Perrotin
The paper introduces CLEAR, an agentic framework designed to improve the reliability of large language models (LLMs) in medical contexts by adjudicating evidence from multiple sources. CLEAR generates candidate answers from three distinct pathways—parametric knowledge, locally curated corpora, and dynamically retrieved evidence—and then uses an aggregation verifier to evaluate agreement and conflict among these sources. An adjudication module decides whether to preserve or revise conclusions, employing override-guard and challenge-audit mechanisms, and initiates targeted follow-up searches when conflicts remain unresolved.
By Shuai Wang, Yize Zhao, Qingyu Chen
The paper introduces a coverage-aware virtual IMU augmentation framework for human activity recognition. It selects diverse and scarce data points in a learned sensor embedding space, generates virtual IMU samples as prompts, ranks them by proximity and label consistency, and incorporates them into training with reliability-based weights. Experiments on public benchmarks demonstrate consistent performance gains over existing baselines, with ablation studies confirming the framework’s effectiveness.
By Jiayuan Gao, Yingwei Zhang, Ziyao Tang, Yuejia Ma, Yuanzhe Chen, Shuchao Song, Boshi Tang
Emotion recognition in conversation (ERC) is a production capability behind agent-assist prompts, escalation routing, and post-call analytics in contact-center-as-a-service (CCaaS) platforms, where co...