-- Early detection of dementia is critical for timely medical intervention and improved patient outcomes. Neuropsychological tests are widely used for cognitive assessment but have traditionally relied on manual scoring. Automatic dementia classification (ADC) systems aim to infer cognitive decline directly from speech recordings of such tests. We propose Demenba, a novel ADC framework based on state space models, which scale linearly in memory and computation with sequence length. Trained on over 1,000 hours of cognitive assessments administered to Framingham Heart Study participants, some of whom were diagnosed with dementia through adjudicated review, our method outperforms prior approaches in fine-grained dementia classification by 21%, while using fewer parameters. We further analyze its scaling behavior and demonstrate that our model gains additional improvement when fused with large language models, paving the way for more transparent and scalable dementia assessment tools. Dementia, including Alzheimer's disease, is a progressive neurodegenerative condition that severely impairs memory, reasoning, communication, and other cognitive functions.

Generative chemical language models (CLMs) have demonstrated strong capabilities in molecular design, yet their impact in drug discovery remains limited by the absence of reliable reward signals and the lack of interpretability in their outputs. We present SAFE-T, a generalist chemical modeling framework that conditions on biological context -- such as protein targets or mechanisms of action -- to prioritize and design molecules without relying on structural information or engineered scoring functions. SAFE-T models the conditional likelihood of fragment-based molecular sequences given a biological prompt, enabling principled scoring of molecules across tasks such as virtual screening, drug-target interaction prediction, and activity cliff detection. Moreover, it supports goal-directed generation by sampling from this learned distribution, aligning molecular design with biological objectives. In comprehensive zero-shot evaluations across predictive (LIT-PCBA, DAVIS, KIBA, ACNet) and generative (DRUG, PMO) benchmarks, SAFE-T consistently achieves performance comparable to or better than existing approaches while being significantly faster. Fragment-level attribution further reveals that SAFE-T captures known structure-activity relationships, supporting interpretable and biologically grounded design. Together with its computational efficiency, these results demonstrate that conditional generative CLMs can unify scoring and generation to accelerate early-stage drug discovery.

Designing experiments and result interpretations are core scientific competencies, particularly in biology, where researchers perturb complex systems to uncover the underlying systems. Recent efforts to evaluate the scientific capabilities of large language models (LLMs) fail to test these competencies because wet-lab experimentation is prohibitively expensive: in expertise, time and equipment. We introduce SciGym, a first-in-class benchmark that assesses LLMs' iterative experiment design and analysis abilities in open-ended scientific discovery tasks. SciGym overcomes the challenge of wet-lab costs by running a dry lab of biological systems. These models, encoded in Systems Biology Markup Language, are efficient for generating simulated data, making them ideal testbeds for experimentation on realistically complex systems. We evaluated six frontier LLMs on 137 small systems, and released a total of 350 systems. Our evaluation shows that while more capable models demonstrated superior performance, all models' performance declined significantly as system complexity increased, suggesting substantial room for improvement in the scientific capabilities of LLM agents.

Blending visual and textual concepts into a new visual concept is a unique and powerful trait of human beings that can fuel creativity. However, in practice, cross-modal conceptual blending for humans is prone to cognitive biases, like design fixation, which leads to local minima in the design space. In this paper, we propose a T2I diffusion adapter "IT-Blender" that can automate the blending process to enhance human creativity. Prior works related to cross-modal conceptual blending are limited in encoding a real image without loss of details or in disentangling the image and text inputs. To address these gaps, IT-Blender leverages pretrained diffusion models (SD and FLUX) to blend the latent representations of a clean reference image with those of the noisy generated image. Combined with our novel blended attention, IT-Blender encodes the real reference image without loss of details and blends the visual concept with the object specified by the text in a disentangled way. Our experiment results show that IT-Blender outperforms the baselines by a large margin in blending visual and textual concepts, shedding light on the new application of image generative models to augment human creativity.

We introduce RegionFocus, a visual test-time scaling approach for Vision Language Model Agents. Understanding webpages is challenging due to the visual complexity of GUI images and the large number of interface elements, making accurate action selection difficult. Our approach dynamically zooms in on relevant regions, reducing background clutter and improving grounding accuracy. To support this process, we propose an image-as-map mechanism that visualizes key landmarks at each step, providing a transparent action record and enables the agent to effectively choose among action candidates. Even with a simple region selection strategy, we observe significant performance gains of 28+\% on Screenspot-pro and 24+\% on WebVoyager benchmarks on top of two state-of-the-art open vision language model agents, UI-TARS and Qwen2.5-VL, highlighting the effectiveness of visual test-time scaling in interactive settings. We achieve a new state-of-the-art grounding performance of 61.6\% on the ScreenSpot-Pro benchmark by applying RegionFocus to a Qwen2.5-VL-72B model. Our code will be released publicly at https://github.com/tiangeluo/RegionFocus.

Large Language Models (LLMs) guardrail systems are designed to protect against prompt injection and jailbreak attacks. However, they remain vulnerable to evasion techniques. We demonstrate two approaches for bypassing LLM prompt injection and jailbreak detection systems via traditional character injection methods and algorithmic Adversarial Machine Learning (AML) evasion techniques. Through testing against six prominent protection systems, including Microsoft's Azure Prompt Shield and Meta's Prompt Guard, we show that both methods can be used to evade detection while maintaining adversarial utility achieving in some instances up to 100% evasion success. Furthermore, we demonstrate that adversaries can enhance Attack Success Rates (ASR) against black-box targets by leveraging word importance ranking computed by offline white-box models. Our findings reveal vulnerabilities within current LLM protection mechanisms and highlight the need for more robust guardrail systems.

Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in vision-language understanding, reasoning, and generation. However, they struggle with tasks requiring fine-grained localization and reasoning in high-resolution images. This constraint stems from the fact that MLLMs are fine-tuned with fixed image resolution to align with the pre-trained image encoder used in MLLM. Consequently, feeding high-resolution images directly into MLLMs leads to poor generalization due to a train-test resolution discrepancy, while downsampling these images-although ensuring consistency-compromises fine-grained visual details and ultimately degrades performance. To address this challenge, we propose Extract Candidate then Predict (ECP), a novel training-free, task-agnostic two-stage framework designed to enhance MLLM performance on high-resolution images. The key intuition behind ECP is that while MLLMs struggle with high-resolution images, their predictions on downsampled images still contain implicit localization cues. By first identifying candidate region using the coarse prediction and then predicting the final output based on candidate region, ECP effectively preserves fine-grained details while mitigating the challenges posed by high-resolution data. We validate our framework on 4K GUI grounding and 4K, 8K MLLM perception, achieving +21.3%, +5.8%, +5.2% absolute improvement compared to baseline respectively, demonstrating its effectiveness. Code is available at https://github.com/yenncye/ECP.

Natural language-based assessment (NLA) is an approach to second language assessment that uses instructions - expressed in the form of can-do descriptors - originally intended for human examiners, aiming to determine whether large language models (LLMs) can interpret and apply them in ways comparable to human assessment. In this work, we explore the use of such descriptors with an open-source LLM, Qwen 2.5 72B, to assess responses from the publicly available S&I Corpus in a zero-shot setting. Our results show that this approach - relying solely on textual information - achieves competitive performance: while it does not outperform state-of-the-art speech LLMs fine-tuned for the task, it surpasses a BERT - based model trained specifically for this purpose. NLA proves particularly effective in mismatched task settings, is generalis-able to other data types and languages, and offers greater in-terpretability, as it is grounded in clearly explainable, widely applicable language descriptors.

AI has driven significant progress in the nutrition field, especially through multimedia-based automatic dietary assessment. However, existing automatic dietary assessment systems often overlook critical non-visual factors, such as recipe-specific ingredient substitutions that can significantly alter nutritional content, and rarely account for individual dietary needs, including allergies, restrictions, cultural practices, and personal preferences. In Switzerland, while food-related information is available, it remains fragmented, and no centralized repository currently integrates all relevant nutrition-related aspects within a Swiss context. To bridge this divide, we introduce the Swiss Food Knowledge Graph (SwissFKG), the first resource, to our best knowledge, to unite recipes, ingredients, and their substitutions with nutrient data, dietary restrictions, allergen information, and national nutrition guidelines under one graph. We establish a LLM-powered enrichment pipeline for populating the graph, whereby we further present the first benchmark of four off-the-shelf (<70 B parameter) LLMs for food knowledge augmentation. Our results demonstrate that LLMs can effectively enrich the graph with relevant nutritional information. Our SwissFKG goes beyond recipe recommendations by offering ingredient-level information such as allergen and dietary restriction information, and guidance aligned with nutritional guidelines. Moreover, we implement a Graph-RAG application to showcase how the SwissFKG's rich natural-language data structure can help LLM answer user-specific nutrition queries, and we evaluate LLM-embedding pairings by comparing user-query responses against predefined expected answers. As such, our work lays the foundation for the next generation of dietary assessment tools that blend visual, contextual, and cultural dimensions of eating.

--Unmanned Aerial V ehicles (UA Vs) are vital for public safety, particularly in wildfire monitoring, where early detection minimizes environmental impact. In UA V-Assisted Wildfire Monitoring (UA WM) systems, joint optimization of sensor transmission scheduling and velocity is critical for minimizing Age of Information (AoI) from stale sensor data. Deep Reinforcement Learning (DRL) has been used for such optimization; however, its limitations such as low sampling efficiency, simulation-to-reality gaps, and complex training render it unsuitable for time-critical applications like wildfire monitoring. This paper introduces a new online Flight Resource Allocation scheme based on LLM-Enabled In-Context Learning (FRSICL) to jointly optimize the UA V's flight control and data collection schedule along the trajectory in real time, thereby asymptotically minimizing the average AoI across ground sensors. In contrast to DRL, FRSICL generates data collection schedules and controls velocity using natural language task descriptions and feedback from the environment, enabling dynamic decision-making without extensive retraining. Simulation results confirm the effectiveness of the proposed FRSICL compared to Proximal Policy Optimization (PPO) and Nearest-Neighbor baselines. Nowadays, Unmanned Aerial V ehicles (UA Vs) have a wide range of applications in public safety [1], energy [2], and environmental monitoring [3]. Public safety UA Vs serve critical roles in emergency operations, including search and rescue (SAR), wildfire surveillance, and disaster management.