A Cornell-led research team has developed an artificial intelligence-powered ring equipped with micro-sonar technology that can continuously and in real time track fingerspelling in American Sign Language (ASL). In its current form, SpellRing could be used to enter text into computers or smartphones via fingerspelling, which is used in ASL to spell out words without corresponding signs, such as proper nouns, names and technical terms. With further development, the device could potentially be used to continuously track entire signed words and sentences. "Many other technologies that recognize fingerspelling in ASL have not been adopted by the deaf and hard-of-hearing community because the hardware is bulky and impractical," said Hyunchul Lim, a doctoral student in the field of information science. "We sought to develop a single ring to capture all of the subtle and complex finger movement in ASL." Lim is lead author of "SpellRing: Recognizing Continuous Fingerspelling in American Sign Language using a Ring," which will be presented at the Association of Computing Machinery's conference on Human Factors in Computing Systems (CHI), April 26-May 1 in Yokohama, Japan.

Intent, typically clearly formulated and planned, functions as a cognitive framework for reasoning and problem-solving. This paper introduces the concept of Speaking with Intent (SWI) in large language models (LLMs), where the explicitly generated intent encapsulates the model's underlying intention and provides high-level planning to guide subsequent analysis and communication. By emulating deliberate and purposeful thoughts in the human mind, SWI is hypothesized to enhance the reasoning capabilities and generation quality of LLMs. Extensive experiments on mathematical reasoning benchmarks consistently demonstrate the superiority of Speaking with Intent over Baseline (i.e., generation without explicit intent). Moreover, SWI outperforms answer-trigger prompting methods Chain-of-Thought and Plan-and-Solve and maintains competitive performance with the strong method ARR (Analyzing, Retrieving, and Reasoning). Additionally, the effectiveness and generalizability of SWI are solidified on reasoning-intensive question answering (QA) and text summarization benchmarks, where SWI brings consistent improvement to the Baseline generation. In text summarization, SWI-generated summaries exhibit greater accuracy, conciseness, and factual correctness, with fewer hallucinations. Furthermore, human evaluations verify the coherence, effectiveness, and interpretability of the intent produced by SWI. This proof-of-concept study creates a novel avenue for enhancing LLMs' reasoning abilities with cognitive notions.

Neurosymbolic programs combine deep learning with symbolic reasoning to achieve better data efficiency, interpretability, and generalizability compared to standalone deep learning approaches. However, existing neurosymbolic learning frameworks implement an uneasy marriage between a highly scalable, GPU-accelerated neural component with a slower symbolic component that runs on CPUs. We propose Lobster, a unified framework for harnessing GPUs in an end-to-end manner for neurosymbolic learning. Lobster maps a general neurosymbolic language based on Datalog to the GPU programming paradigm. This mapping is implemented via compilation to a new intermediate language called APM. The extra abstraction provided by APM allows Lobster to be both flexible, supporting discrete, probabilistic, and differentiable modes of reasoning on GPU hardware with a library of provenance semirings, and performant, implementing new optimization passes. We demonstrate that Lobster programs can solve interesting problems spanning the domains of natural language processing, image processing, program reasoning, bioinformatics, and planning. On a suite of 8 applications, Lobster achieves an average speedup of 5.3x over Scallop, a state-of-the-art neurosymbolic framework, and enables scaling of neurosymbolic solutions to previously infeasible tasks.

Although applying Mixture of Experts to large language models for learning new tasks is widely regarded as an effective strategy for continuous learning, there still remain two major challenges: (1) As the number of tasks grows, simple parameter expansion strategies can lead to excessively large models. (2) Modifying the parameters of the existing router results in the erosion of previously acquired knowledge. In this paper, we present an innovative framework named LLaVA-CMoE, which is a continuous Mixture of Experts (MoE) architecture without any replay data. Specifically, we have developed a method called Probe-Guided Knowledge Extension (PGKE), which employs probe experts to assess whether additional knowledge is required for a specific layer. This approach enables the model to adaptively expand its network parameters based on task distribution, thereby significantly improving the efficiency of parameter expansion. Additionally, we introduce a hierarchical routing algorithm called Probabilistic Task Locator (PTL), where high-level routing captures inter-task information and low-level routing focuses on intra-task details, ensuring that new task experts do not interfere with existing ones. Our experiments shows that our efficient architecture has substantially improved model performance on the Coin benchmark while maintaining a reasonable parameter count.

Objective: We aim to investigate long-term robotic surgical skill acquisition among surgical residents and the effects of training intervals and fatigue on performance. Methods: For six months, surgical residents participated in three training sessions once a month, surrounding a single 26-hour hospital shift. In each shift, they participated in training sessions scheduled before, during, and after the shift. In each training session, they performed three dry-lab training tasks: Ring Tower Transfer, Knot-Tying, and Suturing. We collected a comprehensive dataset, including videos synchronized with kinematic data, activity tracking, and scans of the suturing pads. Results: We collected a dataset of 972 trials performed by 18 residents of different surgical specializations. Participants demonstrated consistent performance improvement across all tasks. In addition, we found variations in between-shift learning and forgetting across metrics and tasks, and hints for possible effects of fatigue. Conclusion: The findings from our first analysis shed light on the long-term learning processes of robotic surgical skills with extended intervals and varying levels of fatigue. Significance: This study lays the groundwork for future research aimed at optimizing training protocols and enhancing AI applications in surgery, ultimately contributing to improved patient outcomes. The dataset will be made available upon acceptance of our journal submission.

Recent Large Reasoning Models (LRMs), such as DeepSeek-R1 and OpenAI o1, have demonstrated strong performance gains by scaling up the length of Chain-of-Thought (CoT) reasoning during inference. However, a growing concern lies in their tendency to produce excessively long reasoning traces, which are often filled with redundant content (e.g., repeated definitions), over-analysis of simple problems, and superficial exploration of multiple reasoning paths for harder tasks. This inefficiency introduces significant challenges for training, inference, and real-world deployment (e.g., in agent-based systems), where token economy is critical. In this survey, we provide a comprehensive overview of recent efforts aimed at improving reasoning efficiency in LRMs, with a particular focus on the unique challenges that arise in this new paradigm. We identify common patterns of inefficiency, examine methods proposed across the LRM lifecycle, i.e., from pretraining to inference, and discuss promising future directions for research. To support ongoing development, we also maintain a real-time GitHub repository tracking recent progress in the field. We hope this survey serves as a foundation for further exploration and inspires innovation in this rapidly evolving area.

We introduce OpenHuEval, the first benchmark for LLMs focusing on the Hungarian language and specifics. OpenHuEval is constructed from a vast collection of Hungarian-specific materials sourced from multiple origins. In the construction, we incorporated the latest design principles for evaluating LLMs, such as using real user queries from the internet, emphasizing the assessment of LLMs' generative capabilities, and employing LLM-as-judge to enhance the multidimensionality and accuracy of evaluations. Ultimately, OpenHuEval encompasses eight Hungarian-specific dimensions, featuring five tasks and 3953 questions. Consequently, OpenHuEval provides the comprehensive, in-depth, and scientifically accurate assessment of LLM performance in the context of the Hungarian language and its specifics. We evaluated current mainstream LLMs, including both traditional LLMs and recently developed Large Reasoning Models. The results demonstrate the significant necessity for evaluation and model optimization tailored to the Hungarian language and specifics. We also established the framework for analyzing the thinking processes of LRMs with OpenHuEval, revealing intrinsic patterns and mechanisms of these models in non-English languages, with Hungarian serving as a representative example. We will release OpenHuEval at https://github.com/opendatalab/OpenHuEval .

Pretrained Bayesian Non-parametric Knowledge Prior in Robotic Long-Horizon Reinforcement Learning Y uan Meng 1, Xiangtong Y ao 1, Kejia Chen 1, Y ansong Wu 1, Liding Zhang 1, Zhenshan Bing 2,, and Alois Knoll 1 IEEE fellow Abstract -- Reinforcement learning (RL) methods typically learn new tasks from scratch, often disregarding prior knowledge that could accelerate the learning process. While some methods incorporate previously learned skills, they usually rely on a fixed structure, such as a single Gaussian distribution, to define skill priors. This rigid assumption can restrict the diversity and flexibility of skills, particularly in complex, long-horizon tasks. In this work, we introduce a method that models potential primitive skill motions as having non-parametric properties with an unknown number of underlying features. We utilize a Bayesian non-parametric model, specifically Dirichlet Process Mixtures, enhanced with birth and merge heuristics, to pre-train a skill prior that effectively captures the diverse nature of skills. Additionally, the learned skills are explicitly trackable within the prior space, enhancing interpretability and control. Our findings show that a richer, non-parametric representation of skill priors significantly improves both the learning and execution of challenging robotic tasks. All data, code, and videos are available at https://ghiara.github.io/HELIOS/.

Large language models are pre-trained on ever-growing token budgets under the assumption that better pre-training performance translates to improved downstream models. In this work, we challenge this assumption and show that extended pre-training can make models harder to fine-tune, leading to degraded final performance. We term this phenomenon catastrophic overtraining. For example, the instruction-tuned OLMo-1B model pre-trained on 3T tokens leads to over 2% worse performance on multiple standard LLM benchmarks than its 2.3T token counterpart. Through controlled experiments and theoretical analysis, we show that catastrophic overtraining arises from a systematic increase in the broad sensitivity of pre-trained parameters to modifications, including but not limited to fine-tuning. Our findings call for a critical reassessment of pre-training design that considers the downstream adaptability of the model.

In augmented reality (AR), where digital content is overlaid onto the real world, realistic thermal feedback has been shown to enhance immersion. Yet current thermal feedback devices, heavily influenced by the needs of virtual reality, often hinder physical interactions and are ineffective for immersion in AR. To bridge this gap, we have identified three design considerations relevant for AR thermal feedback: indirect feedback to maintain dexterity, thermal passthrough to preserve real-world temperature perception, and spatiotemporal rendering for dynamic sensations. We then created a unique and innovative thermal feedback device that satisfies these criteria. Human subject experiments assessing perceptual sensitivity, object temperature matching, spatial pattern recognition, and moving thermal stimuli demonstrated the impact of our design, enabling realistic temperature discrimination, virtual object perception, and enhanced immersion. These findings demonstrate that carefully designed thermal feedback systems can bridge the sensory gap between physical and virtual interactions, enhancing AR realism and usability.