As neural theorem provers become increasingly agentic, the ability to interpret and act on compiler feedback is critical. However, existing Lean datasets consist almost exclusively of correct proofs, offering little supervision for understanding and repairing failures. We study Lean proof repair as a supervised learning problem: given an erroneous proof and compiler feedback, predict both a corrected proof and a natural-language diagnosis grounded in the same feedback. We introduce APRIL (Automated Proof Repair in Lean), a dataset of […]

Ver mais

Neural network weights are typically viewed as the end product of training, while most deep learning research focuses on data, features, and architectures. However, recent advances show that the set of all possible weight values (weight space) itself contains rich structure: pretrained models form organized distributions, exhibit symmetries, and can be embedded, compared, or even generated. Understanding such structures has tremendous impact on how neural networks are analyzed and compared, and on how knowledge is transferred across models, […]

Ver mais

arXiv:2604.01410v1 Announce Type: new Abstract: Text production (and translations) proceeds in the form of stretches of typing, interrupted by keystroke pauses. It is often assumed that fast typing reflects unchallenged/automated translation production while long(er) typing pauses are indicative of translation problems, hurdles or difficulties. Building on a long discussion concerning the determination of pause thresholds that separate automated from presumably reflective translation processes (O’Brien, 2006; Alves and Vale, 2009; Timarova et al., 2011; Dragsted and Carl, 2013; Lacruz […]

Ver mais

arXiv:2601.08892v1 Announce Type: new Abstract: The rise of online counseling services has highlighted the need for effective training methods for future counselors. This paper extends research on VirCo, a Virtual Client for Online Counseling, designed to complement traditional role-playing methods in academic training by simulating realistic client interactions. Building on previous work, we introduce a new dataset incorporating adversarial attacks to test the ability of large language models (LLMs) to maintain their assigned roles (role-consistency). The study focuses […]

Ver mais

arXiv:2603.25841v1 Announce Type: new Abstract: Current multimodal large language models (MLLMs) cannot effectively utilize eye-gaze information for video understanding, even when gaze cues are supplied via visual overlays or text descriptions. We introduce GazeQwen, a parameter efficient approach that equips an open-source MLLM with gaze awareness through hidden-state modulation. At its core is a compact gaze resampler (~1-5 M trainable parameters) that encodes V-JEPA 2.1 video features together with fixation-derived positional encodings and produces additive residuals injected into […]

Ver mais

A new working research from Perplexity and Harvard offers field evidence on what AI agents do to knowledge work. It draws on production data from two Perplexity products: Search and Computer. The setup is a natural comparison. Search is a conversational answer engine. Computer is an agent that plans and executes tasks end to end. The same users touch both products, so the team can hold the task roughly constant. What the Study Actually Measures The research study […]

Ver mais

I have been working as a Business Analyst (BA) in teams of various scales for over 7 years. During this time, I’ve frequently encountered a misunderstanding of the BA’s role and tasks from a developer’s perspective. In this article, I want to share my experience to help developers build effective communication with their BA and extract maximum value from this collaboration. 1. Introduction Throughout my professional journey, I’ve often seen the opinion that a Business Analyst is just […]

Ver mais

IBM plans to use frontier artificial intelligence in cybersecurity, joining hands with OpenAI Daybreak Cyber Partner Program. This move plans to help proprietary city bodies protect themselves against cyber threats. Building on the recently declared project Lightwell, IBM introduces a new application safety service that leverages OpenAI models’ capabilities to nitpick and validate software vulnerabilities. The project emphasizes the safe use of advanced artificial intelligence, governance, and building perseverance across the software supply chain. What Is the Significance […]

Ver mais