Search: “llm”

arXiv:2604.13288v1 Announce Type: new Abstract: We present a unified pipeline for synthesizing high-quality Quechua and Spanish speech for the Peruvian Constitution using three state-of-the-art text-t

arXiv:2604.13942v1 Announce Type: new Abstract: Recent vision-language-action (VLA) systems have demonstrated strong capabilities in embodied manipulation. However, most existing VLA policies rely on

arXiv:2604.13871v1 Announce Type: new Abstract: Deep neural networks (DNNs) deliver state-of-the-art accuracy on regression and classification tasks, yet two structural deficits persistently obstruct

HOLY 🤯 The one and only @elder_plinius just dropped an unlocked Gemma 4 E4B, and the specs are INSANE. Look at the performance shifts: → Refusal rate: 98.8% down to 2.1% (!!) → Compliance: 1.2% up to

arXiv:2604.13686v1 Announce Type: new Abstract: While Large Language Models (LLMs) have significantly advanced Text-to-SQL performance, existing benchmarks predominantly focus on Western contexts and

GPT-Rosalind is a frontier reasoning model developed by OpenAI, specifically designed to support research applications in biology, drug discovery, and translational medicine. The model was introduced

arXiv:2512.10605v2 Announce Type: replace Abstract: We propose LEO-RobotAgent, a general-purpose language-driven intelligent agent framework for robots. Under this framework, LLMs can operate differen

Lots of major improvements to Codex! Computer use is a real update for me; it feels even more useful than I expected. It can use all of the apps on your Mac, in parallel and without interfering with y

arXiv:2604.13695v1 Announce Type: new Abstract: Reliable and interpretable decision-making is essential in medical imaging, where diagnostic outcomes directly influence patient care. Despite advances

arXiv:2604.14004v1 Announce Type: cross Abstract: Memory-based self-evolution has emerged as a promising paradigm for coding agents. However, existing approaches typically restrict memory utilization

arXiv:2604.13828v1 Announce Type: new Abstract: User simulators are essential for the scalable training and evaluation of interactive AI systems. However, existing approaches often rely on shallow use

arXiv:2510.07019v3 Announce Type: replace Abstract: Transformers excel at sequence modeling but face quadratic complexity, while linear attention offers improved efficiency but often compromises recal

arXiv:2604.14073v1 Announce Type: new Abstract: Resolving and rewriting references is fundamental in programming languages. Motivated by a real-world decompilation task, we abstract reference rewritin

arXiv:2601.11340v2 Announce Type: replace Abstract: Chain-of-Thought reasoning has significantly enhanced the problem-solving capabilities of Large Language Models. Unfortunately, current models gener

OpenAI's Codex now features background computer use that lets multiple AI agents operate a Mac simultaneously without disrupting the user's own work. The update allows Codex to access all other apps o

arXiv:2602.07924v2 Announce Type: replace Abstract: Securing petroleum infrastructure requires balancing autonomous system efficiency with human judgment for threat escalation, a challenge unaddressed

arXiv:2604.13356v1 Announce Type: new Abstract: Mechanisms for continued self-improvement of language models without external supervision remain an open challenge. We propose Peer-Predictive Self-Trai

People have been asking for this for years. It wasn't clear how to make it performant enough to be shippable, until earlier today In the next version of Bun `bun test` gets experimental support for pe

Publishers have real questions about AI, but let’s be clear: @waybackmachine isn’t a backdoor for AI scraping. For 30 years, it’s been built for people, not bulk harvesting. We actively monitor to pre

For anyone who has been (inadvisably) taking my pelican riding a bicycle benchmark seriously as a robust way to test models, here are pelicans from this morning's two big model releases - Qwen3.6-35B-

arXiv:2604.13602v1 Announce Type: new Abstract: Reinforcement Learning from Human Feedback (RLHF) and related alignment paradigms have become central to steering large language models (LLMs) and multi

arXiv:2604.13236v1 Announce Type: new Abstract: Semiconductor failure analysis (FA) requires engineers to examine inspection images, correlate equipment telemetry, consult historical defect records, a

arXiv:2604.13331v1 Announce Type: new Abstract: In electronic health record (EHR) mining, learning high-quality representations of medical concepts (e.g., standardized diagnosis, medication, and proce

arXiv:2604.13552v1 Announce Type: new Abstract: Large language models (LLMs) demonstrate strong reasoning capabilities, but their performance often degrades under distribution shift. Existing test-tim

arXiv:2604.14113v1 Announce Type: cross Abstract: GUI grounding, which localizes interface elements from screenshots given natural language queries, remains challenging for small icons and dense layou

A developer successfully optimized Qwen 3.6-35B model to 2-bit quantization, achieving significant performance improvements with only 13GB RAM requirements while maintaining functionality. The work in

arXiv:2604.13776v1 Announce Type: cross Abstract: Watermarking is becoming the default mechanism for AI content authentication, with governance policies and frameworks referencing it as infrastructure

arXiv:2604.12019v1 Announce Type: new Abstract: Although artificial intelligence (AI) agents are increasingly proposed to support potentially longitudinal health tasks, such as symptom management, beh

arXiv:2603.08291v3 Announce Type: replace Abstract: Multimodal Mathematical Reasoning (MMR) has recently attracted increasing attention for its capability to solve mathematical problems involving both

arXiv:2604.12129v1 Announce Type: new Abstract: The transition from stateless model inference to stateful agentic execution is reshaping the systems assumptions underlying modern AI infrastructure. Wh

arXiv:2604.12033v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) increasingly rely on retrieval to answer knowledge-intensive multimodal questions. Existing benchmarks overlook c

arXiv:2604.12660v1 Announce Type: new Abstract: In nonmonotonic reasoning from conditional belief bases, an inference operator satisfying syntax splitting postulates allows for taking only the relevan

arXiv:2604.12308v1 Announce Type: new Abstract: Individuals' concerns about data privacy and AI safety are highly contextualized and extend beyond sensitive patterns. Addressing these issues requires

arXiv:2511.08439v2 Announce Type: replace Abstract: Dataset integrity is fundamental to the safety and reliability of AI systems, especially in autonomous driving. This paper presents a structured fra

arXiv:2604.12293v1 Announce Type: new Abstract: As the number of fatalities involving Autonomous Vehicles increase, the need for a universal method of communicating between vehicles and other agents o

arXiv:2604.12473v1 Announce Type: new Abstract: This position paper looks briefly at the way we attempt to program robotic AI systems. Many AI systems are based on the idea of trying to improve the pe

arXiv:2511.00710v4 Announce Type: replace Abstract: Recent studies posit that Reinforcement Learning with Verifiable Rewards (RLVR) primarily amplifies behaviors inherent to the pre-training distribut

arXiv:2602.04850v2 Announce Type: replace-cross Abstract: Quantum chemistry is a foundational enabling tool for the fields of chemistry, materials science, computational biology and others. Despite of

arXiv:2510.03323v2 Announce Type: replace Abstract: Integrating textual graphs into Large Language Models (LLMs) is promising for complex graph-based QA. However, a key bottleneck is retrieving inform

arXiv:2604.12460v1 Announce Type: new Abstract: Machine learning has become a central research area, with increasing attention devoted to explainable clustering, also known as conceptual clustering, w

arXiv:2603.25326v4 Announce Type: replace Abstract: Interest in the concept of AI-driven harmful manipulation is growing, yet current approaches to evaluating it are limited. This paper introduces a f

arXiv:2604.12559v1 Announce Type: new Abstract: Unstructured model editing aims to update models with real-world text, yet existing methods often memorize text holistically without reliable fine-grain

arXiv:2604.12288v1 Announce Type: cross Abstract: Fine-tuning is a widely used strategy for adapting pre-trained models to new tasks, yet its methodology and theoretical properties in high-dimensional

arXiv:2604.11810v1 Announce Type: cross Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language understanding and generation. However, their immense number

A developer shares a progress update on their personal app built around Ollama, the local large language model runner. The post likely covers new features, improvements, or bug fixes made since a prev

arXiv:2604.12390v1 Announce Type: new Abstract: This paper addresses two limitations of large language models (LLMs) in solving complex problems: (1) their reasoning processes exhibit Bayesian-like st