People living with dementia (PLWDs) face progressively declining abilities in medication management-from simple forgetfulness to complete task breakdown-yet most assistive technologies fail to adapt to these changing needs. This one-size-fits-all approach undermines autonomy, accelerates dependence, and increases caregiver burden. Occupational therapy principles emphasize matching assistance levels to individual capabilities: minimal reminders for those who merely forget, spatial guidance for those who misplace items, and comprehensive multimodal support for those requiring step-by-step instruction. However, existing robotic systems lack this adaptive, graduated response framework essential for maintaining PLWD independence. We present an adaptive multimodal robotic framework using the Pepper robot that dynamically adjusts assistance based on real-time assessment of user needs. Our system implements a hierarchical intervention model progressing from (1) simple verbal reminders, to (2) verbal + gestural cues, to (3) full multimodal guidance combining physical navigation to medication locations with step-by-step verbal and gestural instructions. Powered by LLM-driven interaction strategies and multimodal sensing, the system continuously evaluates task states to provide just-enough assistance-preserving autonomy while ensuring medication adherence. We conducted a preliminary study with healthy adults and dementia care stakeholders in a controlled lab setting, evaluating the system's usability, comprehensibility, and appropriateness of adaptive feedback mechanisms. This work contributes: (1) a theoretically grounded adaptive assistance framework translating occupational therapy principles into HRI design, (2) a multimodal robotic implementation that preserves PLWD dignity through graduated support, and (3) empirical insights into stakeholder perceptions of adaptive robotic care.

We introduce Post-Optimization Model Edit (POME), a new algorithm that enhances the performance of fine-tuned large language models using only their pretrained and fine-tuned checkpoints, without requiring extra data or further optimization. The core idea is to apply a muon-style projection to $ΔW$, the difference between the fine-tuned and pretrained weights. This projection uses truncated singular value decomposition (SVD) to equalize the influence of dominant update directions and prune small singular values, which often represent noise. As a simple post-processing step, POME is completely decoupled from the training pipeline. It requires zero modifications and imposes no overhead, making it universally compatible with any optimizer or distributed framework. POME delivers consistent gains, boosting average performance by +2.5\% on GSM8K and +1.0\% on code generation. Its broad applicability -- from 7B foundation models to 72B RLHF-instructed models -- establishes it as a practical, zero-cost enhancement for any fine-tuning pipeline. Code is available at https://github.com/NUS-HPC-AI-Lab/POME.

Fine-grained emotion recognition aims to identify the emotional type in queries through reasoning and decision-making processes, playing a crucial role in various systems. Recent methods use In-Context Learning (ICL), enhancing the representation of queries in the reasoning process through semantically similar examples, while further improving emotion recognition by explaining the reasoning mechanisms. However, these methods enhance the reasoning process but overlook the decision-making process. This paper investigates decision-making in fine-grained emotion recognition through prototype theory. We show that ICL relies on similarity matching between query representations and emotional prototypes within the model, where emotion-accurate representations are critical. However, semantically similar examples often introduce emotional discrepancies, hindering accurate representations and causing errors. To address this, we propose Emotion In-Context Learning (EICL), which introduces emotionally similar examples and uses a dynamic soft-label strategy to improve query representations in the emotion reasoning process. A two-stage exclusion strategy is then employed to assess similarity from multiple angles, further optimizing the decision-making process. Extensive experiments show that EICL significantly outperforms ICL on multiple datasets.

Large-language-model (LLM) agents are becoming competent at straightforward web tasks, such as opening an item page or submitting a form, but still struggle with objectives that require long-horizon navigation, large-scale information extraction, and reasoning under constraints. DART, a general framework that enables a single LLM to handle such complex chores. DART (i) dynamically decomposes each objective into three focused sub-tasks--navigation, information extraction, and execution--so the model concentrates on one skill at a time, and (ii) continuously re-plans the decomposition as new webpages are revealed, taking advantage of newly discovered filters or shortcuts and avoiding redundant exploration. LLM-powered web agents have recently shown promising abilities in web navigation tasks (Drouin et al., 2024; He et al., 2024; Wei et al., 2025; Y ang et al., 2024a; Pan et al., 2024; Song et al., 2024). Benchmarks such as WebArena (Zhou et al., 2023) demonstrate that these agents achieve reasonable accuracy on simple objectives, highlighting their potential as general-purpose automation tools. However, when the objectives require more complex reasoning and multi-step exploration, the performance of these agents often collapses. As shown in Figure 1, on WebChoreArena (Miyai et al., 2025), a benchmark designed to test higher-complexity web tasks, agents powered by GPT -4o achieve only 8.0% accuracy on tasks across different web domains, far below the 46.6% accuracy on WebArena. This gap highlights a critical weakness of current worflows: while sufficient for simple goals, they are not well equipped for tasks demand multi-step reasoning, long-horizon navigation, and structured information processing. A closer examination reveals that the difficulty arises from cognitive overload. Complex tasks require agents to simultaneously navigate across multiple web pages, extract and track large amounts of information, and reason under constraints. Consider the following task from WebChore-Arena (Miyai et al., 2025): "T ell me the top 3 products with the highest number of reviews in Home Audio of Electronics within the price range of $1,000 to $9,999". As illustrated in Figure 1, product information is distributed across multiple nested web pages. Each page may contain tens of products with attributes such as price and number of reviews.

Conversations with LMs involve two participants: a human user leading the conversation, and an LM assistant responding to the user's request. To satisfy this specific role, LMs are post-trained to be helpful assistants -- optimized to produce exhaustive and well-structured responses, free of ambiguity and grammar errors. User utterances, on the other hand, are rarely perfected, with each user phrasing requests in unique ways, sometimes putting in partial effort at each turn and refining on the fly. To evaluate LM performance in realistic settings, prior work simulated users in multi-turn conversations, often prompting an LLM originally trained to be a helpful assistant to act as a user. However, we show that assistant LMs make for poor user simulators, with the surprising finding that better assistants yield worse simulators. Instead, we introduce purpose-built User Language Models (User LMs) - models post-trained to simulate human users in multi-turn conversations. Through various evaluations, we show how User LMs align better with human behavior and achieve better simulation robustness than existing simulation methods. When leveraging User LMs to simulate coding and math conversations, the performance of a strong assistant (GPT-4o) drops from 74.6% to 57.4%, confirming that more realistic simulation environments lead to assistant struggles as they fail to cope with the nuances of users in multi-turn setups.

Bootstrapped pretraining, i.e., the reuse of a pretrained base model for further pretraining, such as continual pretraining or model growth, is promising at reducing the cost of training language models from scratch. However, its effectiveness remains unclear, especially when applied to overtrained base models. In this work, we empirically study the scaling behavior of bootstrapped pretraining and find that its scaling efficiency diminishes in a predictable manner: The scaling exponent with respect to second-stage pretraining tokens decreases logarithmically with the number of tokens used to pretrain the base model. The joint dependence on first- and second-stage tokens is accurately modeled by a simple scaling law. Such saturation effect reveals a fundamental trade-off in multi-stage pretraining strategies: the more extensively a model is pretrained, the less additional benefit bootstrapping provides. Our findings provide practical insights for efficient language model training and raise important considerations for the reuse of overtrained models.

We present a novel framework that improves the reliability of LLM judges by selectively augmenting LLM with auxiliary evaluation dimensions. Existing LLM judges often miss crucial evaluation dimensions because they fail to recognize the implicit standards underlying human assessments. To address this challenge, we propose the Auto-Prompt Ensemble (APE), an adaptive framework that automatically learns evaluation dimensions from its failure cases. APE incorporates a confidence-based ensemble mechanism to decide when to adopt the judgments from additional evaluation dimensions through a novel confidence estimation approach called Collective Confidence. Extensive experiments demonstrate that APE improves the reliability of LLM Judge across diverse standard benchmarks. For instance, APE enhances GPT-4o agreement rate on Reward Bench from 87.2% to 90.5% in the zero-shot setting. Overall, APE provides a principled approach for LLM Judge to leverage test-time computation, and bridge the evaluation gap between human and LLM judges.

The quality and experience of mobile communication have significantly improved with the introduction of 5G, and these improvements are expected to continue beyond the 5G era. However, vulnerabilities in control-plane protocols, such as Radio Resource Control (RRC) and Non-Access Stratum (NAS), pose significant security threats, such as Blind Denial of Service (DoS) attacks. Despite the availability of existing anomaly detection methods that leverage rule-based systems or traditional machine learning methods, these methods have several limitations, including the need for extensive training data, predefined rules, and limited explainability. Addressing these challenges, we propose a novel anomaly detection framework that leverages the capabilities of Large Language Models (LLMs) in zero-shot mode with unordered data and short natural language attack descriptions within the Open Radio Access Network (O-RAN) architecture. We analyse robustness to prompt variation, demonstrate the practicality of automating the attack descriptions and show that detection quality relies on the semantic completeness of the description rather than its phrasing or length. We utilise an RRC/NAS dataset to evaluate the solution and provide an extensive comparison of open-source and proprietary LLM implementations to demonstrate superior performance in attack detection. We further validate the practicality of our framework within O-RAN's real-time constraints, illustrating its potential for detecting other Layer-3 attacks.

Neural models such as YOLO and HuBERT can be used to detect local properties such as objects ("car") and emotions ("angry") in individual frames of videos and audio clips respectively. The likelihood of these detections is indicated by scores in [0, 1]. Lifting these scores to temporal properties over sequences can be useful for several downstream applications such as query matching (e.g., "does the speaker eventually sound happy in this audio clip?"), and ranked retrieval (e.g., "retrieve top 5 videos with a 10 second scene where a car is detected until a pedestrian is detected"). In this work, we formalize this problem of assigning Scores for TempOral Properties (STOPs) over sequences, given potentially noisy score predictors for local properties. We then propose a scoring function called LogSTOP that can efficiently compute these scores for temporal properties represented in Linear Temporal Logic. Empirically, LogSTOP, with YOLO and HuBERT, outperforms Large Vision / Audio Language Models and other Temporal Logic-based baselines by at least 16% on query matching with temporal properties over objects-in-videos and emotions-in-speech respectively. Similarly, on ranked retrieval with temporal properties over objects and actions in videos, LogSTOP with Grounding DINO and SlowR50 reports at least a 19% and 16% increase in mean average precision and recall over zero-shot text-to-video retrieval baselines respectively.

Large Language Models (LLMs) have achieved remarkable success through imitation learning on vast text corpora, but this paradigm creates a training-generation gap and limits robust reasoning. Reinforcement learning (RL) offers a more data-efficient solution capable of bridging this gap, yet its application has been constrained by a critical data bottleneck: existing RL datasets are orders of magnitude smaller and less diverse than web-scale pre-training corpora. To address this, we introduce the Webscale-RL pipeline, a scalable data engine that systematically converts large-scale pre-training documents into millions of diverse, verifiable question-answer pairs for RL. Using this pipeline, we construct the Webscale-RL dataset, containing 1.2 million examples across more than 9 domains. Our experiments show that the model trained on this dataset significantly outperforms continual pretraining and strong data refinement baselines across a suite of benchmarks. Notably, RL training with our dataset proves substantially more efficient, achieving the performance of continual pre-training with up to 100$\times$ fewer tokens. Our work presents a viable path toward scaling RL to pre-training levels, enabling more capable and efficient language models.