Large language models (LLMs) are increasingly deployed in medical contexts, raising critical concerns about safety, alignment, and susceptibility to adversarial manipulation. While prior benchmarks assess model refusal capabilities for harmful prompts, they often lack clinical specificity, graded harmfulness levels, and coverage of jailbreak-style attacks. We introduce CARES (Clinical Adversarial Robustness and Evaluation of Safety), a benchmark for evaluating LLM safety in healthcare. CARES includes over 18,000 prompts spanning eight medical safety principles, four harm levels, and four prompting styles: direct, indirect, obfuscated, and role-play, to simulate both malicious and benign use cases.

LLMs have made impressive progress, but their growing capabilities also expose them to highly flexible jailbreaking attacks designed to bypass safety alignment. While many existing defenses focus on known types of attacks, it is more critical to prepare LLMs for unseen attacks that may arise during deployment. To address this, we propose a lifelong safety alignment framework that enables LLMs to continuously adapt to new and evolving jailbreaking strategies. Our framework introduces a competitive setup between two components: a Meta-Attacker, trained to actively discover novel jailbreaking strategies, and a Defender, trained to resist them. To effectively warm up the Meta-Attacker, we first leverage the GPT-4o API to extract key insights from a large collection of jailbreak-related research papers. Through iterative training, the first iteration Meta-Attacker achieves a 73% attack success rate (ASR) on RR [80] and a 57% transfer ASR on LAT [53] using only single-turn attacks. Meanwhile, the Defender progressively improves its robustness and ultimately reduces the Meta-Attacker's success rate to just 7%, enabling safer and more reliable deployment of LLMs in open-ended environments.

Training agents to operate under strict constraints during deployment, such as limited resource budgets or stringent safety requirements, presents significant challenges, especially when these constraints render the task complex. In this work, we propose a curriculum learning strategy that gradually tightens constraints during training, enabling the agent to incrementally master the deployment requirements. Inspired by self-paced learning techniques in unconstrained reinforcement learning (RL), our approach facilitates a smoother transition to challenging environments by initially training on simplified versions of the constraints and progressively introducing the full deployment conditions. We provide a theoretical analysis using an RL agent in a binary-tree Markov Decision Process (MDP) to demonstrate that our curriculum strategy can accelerate training relative to a baseline approach that imposes the trajectory constraints from the outset.

Autonomous UI agents powered by AI have tremendous potential to boost human productivity by automating routine tasks such as filing taxes and paying bills. However, a major challenge in unlocking their full potential is security, which is exacerbated by the agent's ability to take action on their user's behalf. Existing tests for prompt injections in web agents either over-simplify the threat by testing unrealistic scenarios or giving the attacker too much power, or look at single-step isolated tasks. To more accurately measure progress for secure web agents, we introduce WASP--a new publicly available benchmark for end-to-end evaluation of Web Agent Security against Prompt injection attacks. Evaluating with WASP shows that even top-tier AI models, including those with advanced reasoning capabilities, can be deceived by simple, low-effort human-written injections in very realistic scenarios. Our end-to-end evaluation reveals a previously unobserved insight: while attacks partially succeed in up to 86% of the case, even state-ofthe-art agents often struggle to fully complete the attacker goals--highlighting the current state of security by incompetence.

Large language models are increasingly capable of handling long-context inputs, but the memory overhead of key-value (KV) cache remains a major bottleneck for general-purpose deployment. While various compression strategies have been explored, sequence-level compression, which drops the full KV caches for certain tokens, is particularly challenging as it can lead to the loss of important contextual information. To address this, we introduce UniGist, a sequence-level long-context compression framework that efficiently preserves context information by replacing raw tokens with special compression tokens (gists) in a fine-grained manner. We adopt a chunk-free training strategy and design an efficient kernel with a gist shift trick, enabling optimized GPU training. Our scheme also supports flexible inference by allowing the actual removal of compressed tokens, resulting in realtime memory savings. Experiments across multiple long-context tasks demonstrate that UniGist significantly improves compression quality, with especially strong performance in detail-recalling tasks and long-range dependency modeling.

In this paper, we propose AdaMSS, an adaptive multi-subspace approach for parameter-efficient fine-tuning of large models. Unlike traditional parameterefficient fine-tuning methods that operate within a large single subspace of the network weights, AdaMSS leverages subspace segmentation to obtain multiple smaller subspaces and adaptively reduces the number of trainable parameters during training, ultimately updating only those associated with a small subset of subspaces most relevant to the target downstream task. By using the lowest-rank representation, AdaMSS achieves more compact expressiveness and finer tuning of the model parameters. Theoretical analyses demonstrate that AdaMSS has better generalization guarantee than LoRA, PiSSA, and other single-subspace low-rankbased methods. Extensive experiments across image classification, natural language understanding, and natural language generation tasks show that AdaMSS achieves comparable performance to full fine-tuning and outperforms other parameterefficient fine-tuning methods in most cases, all while requiring fewer trainable parameters. Notably, on the ViT-Large model, AdaMSS achieves 4.7% higher average accuracy than LoRA across seven tasks, using just 15.4% of the trainable parameters. On RoBERTa-Large, AdaMSS outperforms PiSSA by 7% in average accuracy across six tasks while reducing the number of trainable parameters by approximately 94.4%. These results demonstrate the effectiveness of AdaMSS in parameter-efficient fine-tuning. The code for AdaMSS is available at https: //github.com/jzheng20/AdaMSS.

Best-of-N selection is a key technique for improving the reasoning performance of Large Language Models (LLMs) through increased test-time computation. Current state-of-the-art methods often employ computationally intensive reward models for response evaluation and selection. Reward-free alternatives, like self-consistency and universal self-consistency, are limited in their ability to handle open-ended generation tasks or scale effectively. To address these limitations, we propose self-certainty, a novel and efficient metric that leverages the inherent probability distribution of LLM outputs to estimate response quality without requiring external reward models. We hypothesize that higher distributional self-certainty, aggregated across multiple samples, correlates with improved response accuracy, as it reflects greater confidence in the generated output. Through extensive experiments on various reasoning tasks, we demonstrate that self-certainty (1) scales effectively with increasing sample size N, akin to reward models but without the computational overhead; (2) complements chain-of-thought, improving reasoning performance beyond greedy decoding; and (3) generalizes to open-ended tasks where traditional self-consistency methods fall short. Our findings establish self-certainty as a practical and efficient way for improving LLM reasoning capabilities.

Neural techniques radiance to reconstruct fields (NeRF) and render and 3D photorealistic Gaussian Splatting images. Ho (3DGS) wever, are the popular prerequisite completeness.

Vision-language models (VLMs) often struggle with culturally specific content -- a challenge largely overlooked by existing benchmarks that focus on dominant languages and globalized datasets. We introduce TAIWANVQA, a VQA benchmark designed for Taiwanese culture to evaluate recognition and reasoning in regional contexts. TAIWANVQA contains 2,736 images and 5,472 manually curated questions covering topics such as traditional foods, public signs, festivals, and landmarks. The official benchmark set includes 1,000 images and 2,000 questions for systematic assessment, with the remainder of the data used as training material. Evaluations on state-of-the-art VLMs reveal strong visual recognition but notable weaknesses in cultural reasoning.

We introduce ReplaceMe, a generalized training-free depth pruning method that effectively replaces transformer blocks with a linear operation, while maintaining high performance for low compression ratios. In contrast to conventional pruning approaches that require additional training or fine-tuning, our approach requires only a small calibration dataset that is used to estimate a linear transformation, which approximates the pruned blocks. The estimated linear mapping can be seamlessly merged with the remaining transformer blocks, eliminating the need for any additional network parameters. Our experiments show that ReplaceMe consistently outperforms other training-free approaches and remains highly competitive with state-of-the-art pruning methods that involve extensive retraining/fine-tuning and architectural modifications. Applied to several large language models (LLMs), ReplaceMe achieves up to 25% pruning while retaining approximately 90% of the original model's performance on open benchmarks--without any training or healing steps, resulting in minimal computational overhead.