FISformer proposes replacing the dot-product self-attention in Transformers with a Sugeno-type Fuzzy Inference System (FIS) for time series forecasting. Instead of computing query-key similarities, the model fuzzifies tokens using learnable Gaussian membership functions, applies fuzzy rules, and defuzzifies to produce interaction weights. The paper suggests this approach captures uncertainty and nonlinearity better than standard attention, reporting state-of-the-art results on benchmarks like ETT, ECL, and Weather.

This paper exposes a critical vulnerability in Multimodal Large Language Models (MLLMs): safety alignment fails when harmful intent is embedded in structured visual narratives. The authors introduce ComicJailbreak, a benchmark of 1,167 three-panel comics where panels 1–2 establish narrative context and panel 3 contains a blank speech bubble filled with a paraphrased harmful goal. The model is prompted to "complete the comic" by generating the fourth panel. Across 15 state-of-the-art MLLMs, comic-based attacks achieve ensemble success rates exceeding 90% on Gemini-family models and 85%+ on most open-source models—substantially outperforming plain-text and random-image baselines. The work also reveals that existing defenses (AdaShield, Attack as Defense) trigger severe over-refusal on benign prompts, and that automated safety judges are unreliable on sensitive-but-benign content.

Adversarial Camouflage proposes a wearable privacy defense against facial recognition by optimizing simple face paint patterns (stripes or chevrons) to adversarially minimize embedding similarities across multiple recognition models. The core idea is to restrict the attack space to low-dimensional, user-reproducible geometric parameters (color, angle, width) that can be painted onto semantically valid facial regions, enabling protesters and privacy-conscious individuals to evade automated surveillance without specialized equipment.

This paper tackles camera-agnostic pruning of 3D Gaussian splats for standardized interchange settings like MPEG I-3DGS, where training images, camera parameters, and gradients are unavailable. The authors propose BetaDescPrune, a one-shot post-training method that computes Hybrid Splat Feature Histogram (HSFH) descriptors to capture local geometric and appearance consistency, then models pruning decisions via Beta-distributed evidence with uncertainty-aware confidence scoring. The core insight is that reliable splat importance can be inferred from intrinsic neighborhood structure alone without rendering supervision.

Multi-agent trajectory prediction requires models to understand complex future interactions between agents. This paper proposes braid prediction, an auxiliary task where models classify the crossing relationships (below/over/no\_crossing) between every pair of agents using shared mode embeddings from a DETR-style decoder. By training jointly to predict these topological braid labels alongside trajectories, the model gains future-interaction awareness with negligible inference overhead.

SteelDefectX introduces a vision-language dataset for steel defect detection that aggregates 7,778 images from four existing sources with novel coarse-to-fine textual annotations—ranging from class-level defect descriptions to sample-level attributes (shape, size, depth, position, contrast) generated via GPT-4o. The paper establishes a four-task benchmark showing that rich textual supervision improves cross-material transfer, though it reveals a tension where fine-grained annotations unexpectedly hurt few-shot performance.

This paper tackles the challenge of multi-party consensus-building in travel planning, where agents must negotiate conflicting subjective preferences rather than converge on objective truths. MIND (Multi-agent Inference for Negotiation Dialogue) introduces a Theory-of-Mind-inspired framework where agents infer hidden preference intensities (willingness scores $w \in [1,10]$) from linguistic cues and dynamically adjust their tone between warmth and toughness. The work matters because it extends Multi-Agent Debate (MAD) from factual domains to social coordination problems requiring compromise.

This paper introduces SemEval-2026 Task 12, Abductive Event Reasoning (AER), a shared task requiring systems to identify the most plausible direct cause of a target event from noisy multi-document evidence. The task is cast as an evidence-grounded multiple-choice benchmark with multiple correct answers allowed, capturing challenges like distributed evidence, indirect background factors, and semantically related distractors. With 122 participants and 518 submissions, it represents a significant community effort to benchmark real-world causal reasoning in long-context settings.

SpatialReward addresses the persistent problem of spatial inconsistencies in text-to-image generation, where models produce globally plausible images with incorrect object positioning and relationships. The paper proposes a three-stage verifiable reward model that decomposes free-form prompts into structured constraints, verifies object attributes via expert detectors, and employs vision-language chain-of-thought reasoning to assess complex spatial layouts. Integrated into Flow-GRPO reinforcement learning for Stable Diffusion and FLUX, the approach significantly improves spatial consistency while maintaining overall image quality.

This paper proposes the GenAI SECI model, an update to Nonaka & Takeuchi's classic SECI framework for knowledge creation, designed to leverage generative AI for managing workplace ("Gen-Ba") tacit knowledge. The central innovation is "Digital Fragmented Knowledge"—partial, fragmentary knowledge stored in cyberspace that generative AI aggregates, structures, and recommends to amplify human understanding without requiring full externalization into explicit knowledge. This addresses the urgent problem of transferring expert tacit knowledge as Japan's workforce ages, going beyond conventional KM systems that struggle with the effort required to formalize knowledge.

Ctrl-A addresses automated data augmentation by framing it as a control problem, dynamically adjusting per-operation augmentation strengths via a feedback loop that balances training and validation loss ratios. The method introduces Relative Operation Response (ROR) curves to individually tune transformation distributions without manual initialization or expensive search phases. While it achieves competitive results on CIFAR and SVHN benchmarks with minimal computational overhead (~10% vs. TrivialAugment), the evaluation relies on a modified training setup with extended epochs, raising questions about separability of algorithmic gains from training protocol changes.

Video diffusion models suffer from prohibitive inference costs, but standard image distillation techniques like DMD cause severe oversaturation and temporal collapse when naively extended to video. This work introduces a video-specific distillation framework featuring an adaptive regression loss that dynamically reweights real-data supervision to prevent color artifacts, a temporal variance regularizer to combat static output, and an inference-time frame interpolation module that halves sequence length during high-noise steps to accelerate generation. Applied to Wan2.1, the method enables stable 4-step synthesis with state-of-the-art VBench scores.

ROM tackles overthinking in Large Reasoning Models, where models generate redundant reasoning after reaching correct answers. The core idea is a lightweight streaming detector—an 8.13M parameter head attached to late-layer hidden states of a frozen LLM—that predicts overthinking probability token-by-token and triggers early stopping. It matters because it promises 47% token reduction without full model retraining. We find the method empirically effective but note concerns regarding data scaling limits and labeling costs.

This paper presents Oph-Guid-RAG, a multimodal retrieval-augmented generation system for ophthalmic clinical decision support. Unlike conventional text-based RAG systems, it retrieves full guideline page images using ColQwen2.5, preserving tables, flowcharts, and layout information without OCR errors. The system introduces a controllable retrieval framework with routing and filtering to selectively introduce external evidence, evaluated on a specialized ophthalmology subset extracted from HealthBench.

As users increasingly consult multiple large language models for decision support, a critical question arises: does increasing the number of AI advisors improve accuracy or amplify harmful conformity pressures? This paper investigates how panel size, within-panel consensus, and human-likeness of presentation shape human reliance and decision accuracy across three prediction tasks (income, recidivism, and dating). Through two crowdsourced experiments with 348 participants, the authors reveal a surprising non-monotonic relationship: three AI advisors improve accuracy over a single advisor, but five provide no additional benefit, while unanimous consensus fosters overreliance and wide disagreement creates confusion.

The paper proposes CEBaG, a deterministic hallucination detection method for medical Visual Question Answering that eliminates the need for costly stochastic sampling. By combining token-level predictive variance with visual evidence magnitude derived from log-probabilities, the method detects when models generate responses that contradict input images. This approach achieves superior detection accuracy while reducing computational cost from 20+ generations to just three forward passes, addressing a critical safety bottleneck in clinical AI deployment.

Dyadic is a web-based platform for studying human-human and human-AI conversations through text or voice-based interaction. It attempts to solve the methodological gap in conversation research by providing turnkey tools for experimental manipulation, live monitoring, and in-situ survey delivery during ongoing chats. The core value proposition is lowering barriers to entry for researchers studying dyadic interaction processes without requiring programming expertise.

SegMaFormer proposes a hybrid encoder for 3D medical image segmentation that places Mamba state-space layers in early high-resolution stages (for linear-complexity sequence mixing) and self-attention only in deeper low-resolution stages (where quadratic cost is manageable). The goal is to reduce the prohibitive compute of full 3D attention while preserving global context. With just 2M parameters and 15 GFLOPs, the authors claim competitive results on BraTS, Synapse, and ACDC benchmarks against models up to 75\times larger.

This paper addresses video moment retrieval (VMR) for complex multi-verb queries by proposing a two-stage framework that generates auxiliary short videos via text-to-video diffusion (CogVideoX) as temporal motion priors, then processes them through a linear-time Mamba network. The approach tackles the limitation of static image augmentations—which miss motion dynamics—while avoiding the quadratic complexity of Transformer-based methods on long untrimmed videos. The framework achieves state-of-the-art results on TVR with particular strength on multi-verb queries, though its effectiveness depends heavily on external video generation quality.

This paper identifies a subtle but important distinction between two interpretations of the TD error in reinforcement learning: the explicit form (bootstrapped target minus prediction) commonly used in deep RL, and the implicit form (difference between temporally successive predictions) from the original Sutton (1988) formulation. While equivalent in tabular settings, the authors demonstrate that increasingly nonlinear architectures cause these to diverge significantly, with profound implications for average-reward and differential RL algorithms.