Archive, newest first. Filter by topic, impact and company →
Problem The paper addresses a critical gap in the capability of Supervisory Control and Data Acquisition (SCADA) systems to make rapid decisions in response to alarms without relying on labeled…
Problem This work addresses the limitations of learned dynamics in stochastic transport, particularly the failure to maintain performance when the initial distribution shifts at test time. The authors highlight that…
Recent findings indicate that Anthropic’s Claude Sonnet 4.6 and OpenAI’s GPT-5.5 exhibit gender bias in scenarios involving abuse, suggesting a troubling inconsistency in their ethical frameworks. Specifically, these models reportedly…
Researchers at the Weizmann Institute of Science, led by Michal Irani, have developed an AI tool capable of reconstructing visual stimuli from brain scans, a significant advancement in cognitive neuroscience.…
Problem The paper addresses a significant gap in the capability of existing systems to effectively integrate and interpret scientific evidence. This is particularly relevant in the context of knowledge retrieval,…
Problem This work addresses the gap in designing effective heuristics for combinatorial optimization (CO) problems. The authors propose a novel approach using large language models (LLMs) to enhance algorithmic reasoning…
Problem The paper addresses the sensitivity of large language models (LLMs) to task-irrelevant prompt features, which can lead to suboptimal performance. This issue is particularly relevant in the context of…
Problem This work addresses a significant gap in the capabilities of video scene text editing, particularly focusing on high visual quality, temporal consistency, and edit locality. The authors highlight that…
Problem The paper addresses a significant gap in existing harness optimization techniques, which typically yield a single global harness that is not optimal for every instance. This limitation can lead…
Problem The paper addresses a gap in the capability of existing systems to efficiently identify anomalies in interactive 3D worlds. It highlights the need for robust pipelines that can handle…
{'Problem': 'The paper addresses the limitations of single-shot generation methods in tackling open research problems that require the exploration of multiple conjectures and the retention of intermediate progress. This is…
Problem This work addresses a gap in the capability of generating materials that encompass both visual appearance and construction rules. The authors highlight the limitations of existing methods in effectively…
Problem The paper addresses a gap in existing scaling laws that model recurrence or sparsity in isolation, which limits the understanding of their combined effects on model performance. This work…
Problem This work addresses a significant gap in the coordination between semantic reasoning and physical execution in long-horizon manipulation tasks. The authors highlight the challenges faced by robotic agents in…
Problem This paper addresses a gap in the capability of existing autonomous machine learning engineering (MLE) agents, specifically focusing on the effectiveness of harnesses. The authors highlight that current MLE…
Problem This work addresses a gap in algorithmic statistics concerning the explanation of strings by finite sets. It specifically focuses on the limitations of existing models in capturing the complexity…
Problem This work addresses a gap in the literature regarding the effectiveness of unlearning in multilingual models, specifically focusing on cross-lingual loopholes. The authors highlight that existing methods may not…
Problem The paper addresses a significant gap in the capability of multi-turn language agents, specifically the issue of compounding errors that arise during interactions. These errors can lead to degraded…
{'Problem': 'The paper identifies a significant gap in the reliable evaluation of the speed of computer-use agents (CUAs) due to reproducibility issues in existing benchmarks. The authors argue that current…
Problem This work addresses the gap in handling spatially correlated map uncertainties in Multi-Agent Path Finding (MAPF). The authors highlight that existing methods do not adequately account for these uncertainties,…
Problem Existing methods for computer-use agents (CUAs) primarily depend on sparse outcome rewards, which limits their ability to learn from intermediate actions. This paper addresses the lack of supervision for…
Problem The paper addresses the challenge of perception under insufficient evidence, a critical gap in the literature that affects the reliability of AI systems in real-world applications. This work is…
Problem The paper addresses a gap in the capability of reinforcement learning (RL) environments for large language model (LLM) agents, specifically the need for verifiable rewards, long-horizon interaction, and cost…
Problem The paper addresses a gap in the capability of World Action Models (WAMs) to effectively reuse action experiences across different manipulation tasks. Existing WAMs face challenges in capturing cross-task…
Problem This work addresses the gap in evaluating spoken mathematical reasoning specifically in multi-turn speech-to-speech systems. The authors highlight the need for a structured benchmark to assess how well these…
Problem The paper addresses a significant gap in the capability of efficiently retrieving relevant entries from long-term egocentric video memories. This is particularly relevant in the context of the increasing…
Problem The paper addresses a gap in the capability of language agents to continually improve their performance on complex tasks. The authors highlight the necessity for a systematic approach to…
Problem This work addresses the gap in steering pretrained generative robot policies beyond their initial effective support, particularly in out-of-distribution scenarios. The authors highlight the limitations of existing methods in…
Problem This work addresses a gap in existing unsupervised skill-discovery methods, specifically focusing on the semantic distinctness, interpretability, and expressivity of motor skills. The authors highlight that current approaches lack…
Problem This work addresses the gap in sample efficiency in reinforcement learning (RL) for robot manipulation skills. The authors highlight the challenges faced in traditional RL approaches, particularly in the…
