Multimodal representation learning has largely relied on contrastive models like CLIP that produce a single embedding per sample, which limits their ability to capture relation-dependent relevance. The proposed Relation-Conditioned Multimodal Learning (RCML) framework explicitly conditions embeddings on natural‑language relation descriptions, enabling the same sample to be represented differently under various relational contexts. RCML builds relation‑aware training pairs, incorporates a relation‑conditioned module, and uses a unified contrastive objective to jointly model cross‑modal alignment and relation‑induced structure, achieving superior performance on retrieval and classification tasks across zero‑shot, fine‑tuned, and out‑of‑domain settings.
By Yang Qiao, Yuntong Hu, Bowen Zhu, Hasibul Haque, Liang Zhao
The paper introduces Conflict‑Aware Evidential Deep Learning (C‑EDL), a lightweight post‑hoc method that improves uncertainty quantification for deep learning models. C‑EDL applies diverse, task‑preserving transformations to each input and uses representational disagreement to adjust predictions, thereby reducing overconfident errors on adversarial and out‑of‑distribution data. Experiments demonstrate that C‑EDL outperforms existing Evidential Deep Learning variants and baselines, achieving up to 55 % reduction in coverage for OOD data and 90 % for adversarial data across multiple datasets and attack types.
By Charmaine Barker, Daniel Bethell, Simos Gerasimou
Cocoon is a system architecture designed to enable efficient differentially private training by managing correlated noise across training iterations. The framework stores and processes large noise histories across CPU, GPU, and a memory extension module, optimizes sparse embedding tables, and utilizes near‑memory processing devices. Experiments on an FPGA‑based NMP prototype show performance improvements ranging from 1.23× to 10.82× compared to existing approaches.
By Donghwan Kim, Xin Gu, Jinho Baek, Timothy Lo, Younghoon Min, Kwangsik Shin, Jongryool Kim, Jongse Park, Kiwan Maeng
DEPICT is a new training‑free metric for evaluating text‑to‑image alignment. It replaces fixed reference answers with an agreement rule that compares image‑based and caption‑only responses, weighting questions by how decisively the caption determines them. By merging this agreement score with a holistic score, DEPICT improves negation accuracy dramatically and outperforms existing training‑free metrics while matching or exceeding fine‑tuned evaluators on several benchmarks.
By Vasco Ramos, Sandra Godinho Silva, Joao Magalhaes, Ricardo Rei, Pedro Henrique Martins
Weave Forcing is a training‑free framework that enhances interactive long video generation by enabling compositional memory routing. It uses an LLM to split user prompts into character and background slots, then applies masked memory weaving with semantic masks to selectively retrieve relevant historical references. The method also introduces coverage‑adaptive RoPE to adjust temporal offsets based on reference coverage, reducing visual artifacts and improving cross‑shot consistency while preserving visual quality and text alignment.
By Ziyi Wang, Junchi Yao, Heqian Qiu, Wenbo Shi, Chengjiu Wang, Jinyang He, Binkai Hong, Hongliang Li
The paper presents a new benchmark for automatically evaluating mental health stigma in online text, featuring a fine‑grained taxonomy that covers stigma mode, domain, and specific components across multiple mental health conditions. The authors annotate naturally occurring news and social media posts and test large language models and classifiers for sentiment, toxicity, and hate speech, finding that these models poorly capture stigma and often overpredict it without explicit rules. The benchmark, annotations, exemplar cases, and code are publicly released on GitHub.
By Naomi Baes, Jemima Kang, Nick Haslam, Chris Groot, Alsa Wu, Luc Raszewski, Yulia Otmakhova
OmniConfess is a training‑free method designed to reduce hallucinations in omni‑modal large language models (OmniLLMs) that handle text, images, audio, and video. The approach fixes a candidate response and re‑scores it at token resolution while selectively intervening on evidence from each modality, producing a token‑by‑channel confession that shows which evidence supports each part of the response. Using this confession, OmniConfess preserves grounded content and corrects commitments that rely on irrelevant or contradictory evidence. The authors evaluated the method on OmniHalluBench, a 3,540‑example benchmark drawn from six datasets across multiple modalities and tasks, and found that OmniConfess mitigates hallucinations across diverse settings.
By Huiqiang Rong, Haoran Luo, Hui Feng, Zhonghong Ou, Kaiwen Xue, Guoxin Zhang, Yifan Zhu
The paper introduces a generative graph model that combines mechanistic interpretability with amortized inference by formulating both the generative process and parameter recovery in function space. It extends step graphons to a multifractal construction, enabling a neural inverse operator that can infer parameters for unseen graph sizes. Experiments show the model outperforms a pretrained graph foundation model on zero‑shot generation and matches instance‑specific methods on single‑observation networks, while also sensitively tracking brain state changes in an EEG study.
By Wooseong Choi, Italo'Ivo Lima Dias Pinto, Chen Sun, Gaurav Gupta, Dong Song, Paul Bogdan
The paper introduces ComInsight, a method for generating analytical reports from relational tables by composing verifiable atomic insights. It defines atomic insights as minimal executable analytical units, enumerates them from the database schema, and organizes them into a multi-relational insight graph. Composition operators then fuse these atomic nodes into higher-order conclusions, each accompanied by executable SQL and fine-grained provenance, achieving superior factual correctness, novelty, and structural completeness on three benchmarks.
By Teng Lin, Xinyu Liu, Nan Tang
The Writerslogic team participated in the CLEF 2026 SimpleText shared task, tackling both text simplification (Task 1) and complexity spotting (Task 2). For simplification, they built a multi‑candidate pipeline with GPT‑4o‑mini, selecting the best candidate via a reference‑free heuristic, and their Claude Sonnet 4 submission achieved a SARI of 47.43 and BLEU of 14.21, ranking third overall on the Task 1 leaderboard. For complexity spotting, they fine‑tuned a DeBERTa‑v3‑large NLI model on 350 K labeled pairs, achieving a macro F1 of 0.8081 (0.8085 in an ensemble) on binary over‑generation identification and 0.804 accuracy on multi‑class error classification, placing them second among unique teams.
By David L. Condrey
The article reviews the challenges and opportunities of detecting social bots amid the rise of advanced AI chatbots. It highlights gaps in current detection methods, especially regarding AI-generated conversations, and identifies emerging trends such as synthetic data generation, multimodal cross‑platform detection, low‑resource language support, and federated learning approaches. The authors propose these directions as promising avenues for future research.
By Emilio Ferrara
The World Embedding Benchmark introduces 8,000 simulation-based video cases covering fluid, solid, dynamic, and optical physics, each paired with physical annotations. It supports three tasks—text‑video retrieval, physical‑property regression, and multiple‑choice classification—to assess how well video embeddings capture physical alignment versus quantitative information. Experiments show that while pre‑trained models perform poorly on retrieval and classification, lightweight probes can extract useful physical data, and physics‑specific contrastive training improves alignment but harms regression, highlighting a trade‑off. Retrieval‑augmented generation using these embeddings further enhances the physical fidelity of generated videos.
By Yiqi Liu, Ruifeng Yuan, Yang Wang, Long Li, Fengyu Cai, Hou Pong Chan, Jialin Yu, Hao Zhang, Chenghua Lin, Chenghao Xiao
The study investigates how UK healthcare staff use Google Translate to communicate with patients who speak French or Spanish, focusing on the risks of translating medical abbreviations. Twenty-one staff members from various specialties were interviewed after reviewing translated clinical examples, and the data were analyzed qualitatively to assess awareness of potential safety hazards. The research highlights a gap in understanding how reliance on machine translation might compromise patient care, especially when dealing with abbreviated medical terminology.
By Eleanor Taylor-Stilgoe, F\'elix do Carmo, Constantin Or\u{a}san
The paper introduces ACES, a structured sampling framework for implicit neural representations that separates coverage from importance. ACES builds adaptive spatial partitions to ensure domain coverage and reduce redundant sampling, while applying region-level importance weighting to focus on informative areas. The authors provide theoretical analysis showing reduced gradient variance and potential optimization gains, and demonstrate faster convergence and lower error on scientific field learning tasks compared to uniform and pointwise adaptive sampling.
By Guang Zhao, Xihaier Luo, Huan-Hsin Tseng, Seungjun Lee, Shinjae Yoo, Yihui Ren, Wei Xu
Pincer is a defense mechanism for coding agents that operates at the resource layer, complementing existing tool‑call defenses. It uses a digital twin—an isolated‑context model that learns and enforces dynamic, user‑specific least‑privilege policies—to act as a proxy for the agent’s permission requests. The authors introduce a user‑centric dataset to emulate the learning phase and demonstrate that Pincer outperforms several baselines in both security and utility, especially against adversarial attack types.
By Mayank Rathee, Alexander Stepanov, Shalin Madabhavi, Jinhao Zhu, Raluca Ada Popa, Ion Stoica
The paper introduces CausalBridge, a framework that uses causal structure to assign semantics to unnamed variables in numerical measurements. By discovering a causal graph from the data and solving for variable embeddings constrained by this graph, the method aligns variable meanings with a language model, outperforming association‑based approaches. Experiments on questionnaires and robotics scenarios show high accuracy even when most variable names are masked, enabling rapid and cost‑effective system naming.
By Shuhao Zhang, Xuran Zhou, Han Guo, Pengtao Xie, Yujia Zheng
The paper introduces Spectral Correction Guidance, a training‑free method that uses spectral alignment to detect and correct deviations in guided diffusion trajectories. By comparing intermediate states to an analytic reference spectrum, the approach improves consistency with the forward process and enhances image generation quality. Experiments show consistent gains over baseline guidance in text‑to‑image tasks and on ImageNet, with benefits across guidance scales and fewer denoising steps.
By Gihoon Kim, Taesup Kim
The paper introduces SCAP (Stiefel Cross-Attention Pool), a routing layer that uses a pool of Stiefel filters combined via cross‑attention to create a sample‑specific bilinear map. SCAP addresses the capacity ceiling problem of standard ReEig nonlinearity in SPD networks, where a single filter cannot align multiple domains. Experiments on five cross‑domain EEG motor‑imagery datasets show SCAP improves balanced accuracy over fixed‑filter SPDNet and matches or surpasses three domain‑adaptive baselines on most datasets.
By Isabella C. Maia, Salem Said, Pedro L. C. Rodrigues, Marco Congedo
The study investigates why large language models (LLMs) show different triage performance when answering clinician‑authored vignettes in multiple‑choice versus free‑text formats. Using sparse‑autoencoder features on Gemma 3 and Qwen3 models, the authors find that medical information is encoded similarly in both formats, but at the decision token the multiple‑choice scaffold dominates, with over 91% of attribution coming from scaffold‑peaking features. The effect varies by model, and shuffling option order eliminates simple positional bias, suggesting the format influence is tied to answer selection rather than earlier case processing.
By David Fraile Navarro, Berardino Como, Jialei Sheng, Soundariya Ananthan, Shlomo Berkovsky
MACTS-EM is a new multi‑agent framework for time series forecasting that combines domain‑specialised agents, a meta‑cognitive allocation layer, emergent memory for cross‑domain transfer, multimodal context integration, and adversarial robustness. The authors evaluate the system on financial, climate, energy, and pandemic data, reporting 8‑12% higher accuracy, 22‑27% better zero‑shot transfer, 16‑21% greater resilience to regime shifts, and 15‑18% faster recovery from distribution changes compared to existing methods. These results suggest that collaborative, agent‑based approaches can outperform traditional architectures in complex, real‑world forecasting tasks.
By Ahmad Shahi, Mamehgol Yousefi