arXiv:2603.08420v2 Announce Type: replace-cross Abstract: Self-driving laboratories (SDLs) are rapidly transforming research in chemistry and materials science to accelerate new discoveries. Mobile robot chemists (MRCs) play a pivotal role by autonomously navigating the lab to transport samples, effectively connecting synthesis, analysis, and characterisation equipment. The instruments within an SDL are typically designed or retrofitted to […]
A Quantitative Characterization of Forgetting in Post-Training
arXiv:2603.12163v1 Announce Type: cross Abstract: Continual post-training of generative models is widely used, yet a principled understanding of when and why forgetting occurs remains limited. We develop theoretical results under a two-mode mixture abstraction (representing old and new tasks), proposed by Chen et al. (2025) (arXiv:2510.18874), and formalize forgetting in two forms: (i) mass forgetting, […]
Adapting Dijkstra for Buffers and Unlimited Transfers
arXiv:2603.11729v1 Announce Type: cross Abstract: In recent years, RAPTOR based algorithms have been considered the state-of-the-art for path-finding with unlimited transfers without preprocessing. However, this status largely stems from the evolution of routing research, where Dijkstra-based solutions were superseded by timetable-based algorithms without a systematic comparison. In this work, we revisit classical Dijkstra-based approaches for […]
Agentic Design Review System
arXiv:2508.10745v2 Announce Type: replace Abstract: Evaluating graphic designs involves assessing it from multiple facets like alignment, composition, aesthetics and color choices. Evaluating designs in a holistic way involves aggregating feedback from individual expert reviewers. Towards this, we propose an Agentic Design Review System (AgenticDRS), where multiple agents collaboratively analyze a design, orchestrated by a meta-agent. […]
Computational Pathology in the Era of Emerging Foundation and Agentic AI — International Expert Perspectives on Clinical Integration and Translational Readiness
arXiv:2603.05884v2 Announce Type: replace-cross Abstract: Recent breakthroughs in artificial intelligence through foundation models and agents have accelerated the evolution of computational pathology. Demonstrated performance gains reported across academia in benchmarking datasets in predictive tasks such as diagnosis, prognosis, and treatment response have ignited substantial enthusiasm for clinical application. Despite this development momentum, real world adoption […]
ResearchGym: Evaluating Language Model Agents on Real-World AI Research
arXiv:2602.15112v2 Announce Type: replace Abstract: We introduce ResearchGym, a benchmark and execution environment for evaluating AI agents on end-to-end research. To instantiate this, we repurpose five oral and spotlight papers from ICML, ICLR, and ACL. From each paper’s repository, we preserve the datasets, evaluation harness, and baseline implementations but withhold the paper’s proposed method. This […]
Affect Decoding in Phonated and Silent Speech Production from Surface EMG
arXiv:2603.11715v1 Announce Type: cross Abstract: The expression of affect is integral to spoken communication, yet, its link to underlying articulatory execution remains unclear. Measures of articulatory muscle activity such as EMG could reveal how speech production is modulated by emotion alongside acoustic speech analyses. We investigate affect decoding from facial and neck surface electromyography (sEMG) […]
Stein Variational Evolution Strategies
arXiv:2410.10390v3 Announce Type: replace-cross Abstract: Stein Variational Gradient Descent (SVGD) is a highly efficient method to sample from an unnormalized probability distribution. However, the SVGD update relies on gradients of the log-density, which may not always be available. Existing gradient-free versions of SVGD make use of simple Monte Carlo approximations or gradients from surrogate distributions, […]
From Toil to Thought: Designing for Strategic Exploration and Responsible AI in Systematic Literature Reviews
arXiv:2603.05514v2 Announce Type: replace-cross Abstract: Systematic Literature Reviews (SLRs) are fundamental to scientific progress, yet the process is hindered by a fragmented tool ecosystem that imposes a high cognitive load. This friction suppresses the iterative, exploratory nature of scholarly work. To investigate these challenges, we conducted an exploratory design study with 20 experienced researchers. This […]
Measuring Intent Comprehension in LLMs
arXiv:2506.16584v2 Announce Type: replace-cross Abstract: People judge interactions with large language models (LLMs) as successful when outputs match what they want, not what they type. Yet LLMs are trained to predict the next token solely from text input, not underlying intent. Because written language is an imperfect proxy for intent, and correlations between phrasing and […]
OSCBench: Benchmarking Object State Change in Text-to-Video Generation
arXiv:2603.11698v1 Announce Type: cross Abstract: Text-to-video (T2V) generation models have made rapid progress in producing visually high-quality and temporally coherent videos. However, existing benchmarks primarily focus on perceptual quality, text-video alignment, or physical plausibility, leaving a critical aspect of action understanding largely unexplored: object state change (OSC) explicitly specified in the text prompt. OSC refers […]
Belief Dynamics Reveal the Dual Nature of In-Context Learning and Activation Steering
arXiv:2511.00617v2 Announce Type: replace-cross Abstract: Large language models (LLMs) can be controlled at inference time through prompts (in-context learning) and internal activations (activation steering). Different accounts have been proposed to explain these methods, yet their common goal of controlling model behavior raises the question of whether these seemingly disparate methodologies can be seen as specific […]