RxnBench: A Multimodal Benchmark for Evaluating Large Language Models on Chemical Reaction Understanding from Scientific Literature

The integration of Multimodal Large Language Models (MLLMs) into chemistry promises to revolutionize scientific discovery, yet their ability to comprehend the dense, graphical language of reactions within authentic literature remains underexplored. Here, we introduce RxnBench, a multi-tiered benchmark designed to rigorously evaluate MLLMs on chemical reaction understanding from scientific PDFs. RxnBench comprises two tasks: Single-Figure QA (SF-QA), which tests fine-grained visual perception and mechanistic reasoning using 1,525 questions derived from 305 curated reaction schemes, and Full-Document QA (FD-QA), which challenges models to synthesize information from 108 articles, requiring cross-modal integration of text, schemes, and tables. Our evaluation of MLLMs reveals a critical capability gap: while models excel at extracting explicit text, they struggle with deep chemical logic and precise structural recognition. Notably, models with inference-time reasoning significantly outperform standard architectures, yet none achieve 50\% accuracy on FD-QA. These findings underscore the urgent need for domain-specific visual encoders and stronger reasoning engines to advance autonomous AI chemists.

Multi-Agent Intelligence for Multidisciplinary Decision-Making in Gastrointestinal Oncology

Multimodal clinical reasoning in the field of gastrointestinal (GI) oncology necessitates the integrated interpretation of endoscopic imagery, radiological data, and biochemical markers. Despite the evident potential exhibited by Multimodal Large Language Models (MLLMs), they frequently encounter challenges such as context dilution and hallucination when confronted with intricate, heterogeneous medical histories. In order to address these limitations, a hierarchical Multi-Agent Framework is proposed, which emulates the collaborative workflow of a human Multidisciplinary Team (MDT). The system attained a composite expert evaluation score of 4.60/5.00, thereby demonstrating a substantial improvement over the monolithic baseline. It is noteworthy that the agent-based architecture yielded the most substantial enhancements in reasoning logic and medical accuracy. The findings indicate that mimetic, agent-based collaboration provides a scalable, interpretable, and clinically robust paradigm for automated decision support in oncology.

Untethered thin dielectric elastomer actuated soft robot

Thin dielectric elastomer actuator (DEA) features a unique in-plane configuration, enabling low-profile designs capable of accessing millimetre-scale narrow spaces. However, most existing DEA-powered soft robots require high voltages and wired power connections, limiting their ability to operate in confined environments. This study presents an untethered thin soft robot (UTS-Robot) powered by thin dielectric elastomer actuators (TS-DEA). The robot measures 38 mm in length, 6 mm in height, and weighs just 2.34 grams, integrating flexible onboard electronics to achieve fully untethered actuation. The TS-DEA, operating at resonant frequencies of 86 Hz under a low driving voltage of 220 V, adopts a dual-actuation sandwiched structure, comprising four dielectric elastomer layers bonded to a compressible tensioning mechanism at its core. This design enables high power density actuation and locomotion via three directional friction pads. The low-voltage actuation is achieved by fabricating each elastomer layer via spin coating to an initial thickness of 50 um, followed by biaxial stretching to 8 um. A comprehensive design and modelling framework has been developed to optimise TS-DEA performance. Experimental evaluations demonstrate that the bare TS-DEA achieves a locomotion speed of 12.36 mm/s at resonance, the untethered configuration achieves a locomotion speed of 0.5 mm/s, making it highly suitable for navigating confined and complex environments.

Autonomous Vehicle Path Planning by Searching With Differentiable Simulation

Planning allows an agent to safely refine its actions before executing them in the real world. In autonomous driving, this is crucial to avoid collisions and navigate in complex, dense traffic scenarios. One way to plan is to search for the best action sequence. However, this is challenging when all necessary components - policy, next-state predictor, and critic - have to be learned. Here we propose Differentiable Simulation for Search (DSS), a framework that leverages the differentiable simulator Waymax as both a next state predictor and a critic. It relies on the simulator's hardcoded dynamics, making state predictions highly accurate, while utilizing the simulator's differentiability to effectively search across action sequences. Our DSS agent optimizes its actions using gradient descent over imagined future trajectories. We show experimentally that DSS - the combination of planning gradients and stochastic search - significantly improves tracking and path planning accuracy compared to sequence prediction, imitation learning, model-free RL, and other planning methods.

Self-Correcting Large Language Models: Generation vs. Multiple Choice

Large language models have recently demonstrated remarkable abilities to self-correct their responses through iterative refinement, often referred to as self-consistency or self-reflection. However, the dynamics of this self-correction mechanism may differ substantially depending on whether the model is tasked with open-ended text generation or with selecting the most appropriate response from multiple predefined options. In this paper, we conduct a systematic investigation of these two paradigms by comparing performance trends and error-correction behaviors across various natural language understanding and reasoning tasks, covering language models of different scales and families. Our experimental results reveal distinct patterns of improvement and failure modes: \textit{While open-ended generation often benefits from the flexibility of re-interpretation and compositional refinement, multiple-choice selection can leverage clearer solution boundaries but may be limited by the provided options}. This contrast also reflects the dual demands faced by emerging agentic LLM applications: effective agents must not only generate and refine open-ended plans or explanations, but also make reliable discrete choices when operating within constrained action spaces. Our findings, therefore, highlight that the design of self-correction mechanisms should take into account the interaction between task structure and output space, with implications for both knowledge-intensive reasoning and decision-oriented applications of LLMs.

Queries Are Not Alone: Clustering Text Embeddings for Video Search

The rapid proliferation of video content across various platforms has highlighted the urgent need for advanced video retrieval systems. Traditional methods, which primarily depend on directly matching textual queries with video metadata, often fail to bridge the semantic gap between text descriptions and the multifaceted nature of video content. This paper introduces a novel framework, the Video-Text Cluster (VTC), which enhances video retrieval by clustering text queries to capture a broader semantic scope. We propose a unique clustering mechanism that groups related queries, enabling our system to consider multiple interpretations and nuances of each query. This clustering is further refined by our innovative Sweeper module, which identifies and mitigates noise within these clusters. Additionally, we introduce the Video-Text Cluster-Attention (VTC-Att) mechanism, which dynamically adjusts focus within the clusters based on the video content, ensuring that the retrieval process emphasizes the most relevant textual features. Further experiments have demonstrated that our proposed model surpasses existing state-of-the-art models on five public datasets.

Pulp Motion: Framing-aware multimodal camera and human motion generation

Treating human motion and camera trajectory generation separately overlooks a core principle of cinematography: the tight interplay between actor performance and camera work in the screen space. In this paper, we are the first to cast this task as a text-conditioned joint generation, aiming to maintain consistent on-screen framing while producing two heterogeneous, yet intrinsically linked, modalities: human motion and camera trajectories. We propose a simple, model-agnostic framework that enforces multimodal coherence via an auxiliary modality: the on-screen framing induced by projecting human joints onto the camera. This on-screen framing provides a natural and effective bridge between modalities, promoting consistency and leading to more precise joint distribution. We first design a joint autoencoder that learns a shared latent space, together with a lightweight linear transform from the human and camera latents to a framing latent. We then introduce auxiliary sampling, which exploits this linear transform to steer generation toward a coherent framing modality. To support this task, we also introduce the PulpMotion dataset, a human-motion and camera-trajectory dataset with rich captions, and high-quality human motions. Extensive experiments across DiT- and MAR-based architectures show the generality and effectiveness of our method in generating on-frame coherent human-camera motions, while also achieving gains on textual alignment for both modalities. Our qualitative results yield more cinematographically meaningful framings setting the new state of the art for this task. Code, models and data are available in our \href{https://www.lix.polytechnique.fr/vista/projects/2025_pulpmotion_courant/}{project page}.

Entropy After $\langle \texttt{/Think} \rangle$ for reasoning model early exiting

Large reasoning models show improved performance with longer chains of thought. However, recent work has highlighted (qualitatively) their tendency to overthink, continuing to revise answers even after reaching the correct solution. We quantitatively confirm this inefficiency by tracking Pass@1 for answers averaged over a large number of rollouts and find that the model often begins to always produce the correct answer early in the reasoning, making extra reasoning a waste of tokens. To detect and prevent overthinking, we propose a simple and inexpensive novel signal -- Entropy After </Think> (EAT) -- for monitoring and deciding whether to exit reasoning early. By appending a stop thinking token (</think>) and monitoring the entropy of the following token as the model reasons, we obtain a trajectory that decreases and stabilizes when Pass@1 plateaus; thresholding its variance under an exponential moving average yields a practical stopping rule. Importantly, our approach enables adaptively allocating compute based on the EAT trajectory, allowing us to spend compute in a more efficient way compared with fixing the token budget for all questions. Empirically, on MATH500 and AIME2025, EAT reduces token usage by 13 - 21% without harming accuracy, and it remains effective in black box settings where logits from the reasoning model are not accessible, and EAT is computed with proxy models.

A Multimodal Foundation Model to Enhance Generalizability and Data Efficiency for Pan-cancer Prognosis Prediction

Multimodal data provides heterogeneous information for a holistic understanding of the tumor microenvironment. However, existing AI models often struggle to harness the rich information within multimodal data and extract poorly generalizable representations. Here we present MICE (Multimodal data Integration via Collaborative Experts), a multimodal foundation model that effectively integrates pathology images, clinical reports, and genomics data for precise pan-cancer prognosis prediction. Instead of conventional multi-expert modules, MICE employs multiple functionally diverse experts to comprehensively capture both cross-cancer and cancer-specific insights. Leveraging data from 11,799 patients across 30 cancer types, we enhanced MICE's generalizability by coupling contrastive and supervised learning. MICE outperformed both unimodal and state-of-the-art multi-expert-based multimodal models, demonstrating substantial improvements in C-index ranging from 3.8% to 11.2% on internal cohorts and 5.8% to 8.8% on independent cohorts, respectively. Moreover, it exhibited remarkable data efficiency across diverse clinical scenarios. With its enhanced generalizability and data efficiency, MICE establishes an effective and scalable foundation for pan-cancer prognosis prediction, holding strong potential to personalize tailored therapies and improve treatment outcomes.

GBV-SQL: Guided Generation and SQL2Text Back-Translation Validation for Multi-Agent Text2SQL

While Large Language Models have significantly advanced Text2SQL generation, a critical semantic gap persists where syntactically valid queries often misinterpret user intent. To mitigate this challenge, we propose GBV-SQL, a novel multi-agent framework that introduces Guided Generation with SQL2Text Back-translation Validation. This mechanism uses a specialized agent to translate the generated SQL back into natural language, which verifies its logical alignment with the original question. Critically, our investigation reveals that current evaluation is undermined by a systemic issue: the poor quality of the benchmarks themselves. We introduce a formal typology for "Gold Errors", which are pervasive flaws in the ground-truth data, and demonstrate how they obscure true model performance. On the challenging BIRD benchmark, GBV-SQL achieves 63.23% execution accuracy, a 5.8% absolute improvement. After removing flawed examples, GBV-SQL achieves 96.5% (dev) and 97.6% (test) execution accuracy on the Spider benchmark. Our work offers both a robust framework for semantic validation and a critical perspective on benchmark integrity, highlighting the need for more rigorous dataset curation.