Knowledge catalogue
arXiv:2605.20712v1 Announce Type: new Abstract: Automatic speech recognition replaces typing only when correction costs less than manual entry, a threshold determined by error types, not counts: fixin
arXiv:2605.20602v1 Announce Type: new Abstract: Successive self-training on a language model's own outputs is widely characterized as a process of flattening: diversity drops, distributions narrow, an
Many development teams are familiar with the hesitation that comes right before pushing a new feature live. As AI helps developers write code faster, the gap between rapid code generation and safe pro
arXiv:2605.21135v1 Announce Type: new Abstract: As MT quality increases, interest in enhanced post-editing features such as QE-derived error highlights is growing, yet evidence for their usefulness re
arXiv:2605.20619v1 Announce Type: new Abstract: Scalarization is widely used in multi-objective optimization owing to its simplicity and scalability. In many applications, the goal is to generate solu
arXiv:2605.21318v1 Announce Type: new Abstract: Large language models (LLMs) are highly sensitive to the prompts used to specify task objectives and behavioral constraints. Many recent prompt optimiza
arXiv:2605.21242v1 Announce Type: new Abstract: As robot fleets become more heterogeneous, including humanoids, rovers, quadrupeds, and drones, selecting the right robot for a task becomes a core syst
arXiv:2605.21299v1 Announce Type: new Abstract: Humans effortlessly go beyond literal meanings: If you mow the lawn, I will give you fifty dollars, is typically understood as implying that the speaker
arXiv:2408.08812v2 Announce Type: replace Abstract: Deployed reinforcement learning agents often face safety requirements that are specified only after training, such as new hazard maps, revised risk
arXiv:2605.21097v1 Announce Type: new Abstract: Web content extraction - isolating a page's main content from surrounding boilerplate - is a prerequisite for search indexing, retrieval-augmented gener
arXiv:2605.19988v1 Announce Type: cross Abstract: Documentation has long guided computer system tuning by distilling expert knowledge into per-parameter recommendations. Yet such guides capture only w
arXiv:2605.19316v1 Announce Type: new Abstract: Recent studies in difficulty-controlled reading comprehension item generation have leveraged large language models (LLMs) to produce items by adjusting
arXiv:2605.19950v1 Announce Type: new Abstract: Humans infer emotions by integrating observed multimodal cues with expectations about how affective states may unfold. Existing multimodal large languag
arXiv:2605.18770v1 Announce Type: cross Abstract: We present a collaborative agentic GraphRAG framework for expert analysis of commercial registry data. Public registries are often formally accessible
arXiv:2605.19847v1 Announce Type: cross Abstract: Multi-tenant retrieval-augmented generation (RAG) services advertise per-account differential privacy as the operative leakage boundary: each account'
Build b9239 is a llama.cpp release that includes a fix for the --fit verbosity flag when used with --verbosity 4 . The release provides compiled binaries for multiple platforms including macOS (Apple
b9244 is an intermediate build release of llama.cpp, a C/C++ implementation framework for running large language models with GGUF format support. The release includes pre-compiled binaries for multipl
arXiv:2605.19069v1 Announce Type: cross Abstract: Code-switching -- the natural alternation between two languages within a single utterance -- represents one of the most challenging and under-studied
arXiv:2605.19972v1 Announce Type: cross Abstract: Vector quantization is a fundamental primitive for scalable machine learning systems, enabling memory-efficient storage, fast retrieval, and compresse
arXiv:2605.20165v1 Announce Type: new Abstract: Vision-Language Models (VLMs) achieve strong performance on spatial question answering benchmarks, yet it remains unclear whether such gains reflect gen
arXiv:2605.19806v1 Announce Type: cross Abstract: This paper investigates chunking strategies for retrieval-augmented generation on German statutory law, using the German Civil Code as a structured be
arXiv:2605.19269v1 Announce Type: new Abstract: Transformer training systems are built around dense linear algebra, yet a nontrivial fraction of end-to-end time is spent on surrounding memory-bound op
arXiv:2605.19350v1 Announce Type: cross Abstract: Creating and editing high-quality 3D content remains a central challenge in computer graphics. We address this challenge by introducing CompoSE, a nov
arXiv:2512.14700v2 Announce Type: replace-cross Abstract: Online harassment is a widespread social and public health concern, yet most computational approaches for detecting and addressing harassment
arXiv:2605.19665v1 Announce Type: cross Abstract: Pairwise human preference prediction is central to evaluating code-generation systems, where quality often depends on task-specific trade-offs beyond
arXiv:2605.19966v1 Announce Type: cross Abstract: Optimization-based adversarial suffixes can jailbreak aligned large language models (LLMs) while remaining fluent, weakening static and windowed perpl
arXiv:2605.19859v1 Announce Type: new Abstract: Vision-language models (VLMs) have rapidly evolved into general-purpose multimodal reasoners with strong zero-shot generalization. In this context, VLMs
arXiv:2605.19111v1 Announce Type: cross Abstract: Existing text-to-image (T2I) evaluation metrics mainly assess whether generated images align with information explicitly stated in the prompt, but oft
arXiv:2605.19600v1 Announce Type: new Abstract: In the field of Vision-Language Navigation (VLN), aerial datasets remain limited in their ability to combine scale, diversity, and realism, often relyin
arXiv:2510.13727v2 Announce Type: replace Abstract: Generative AI systems are increasingly assisting and acting on behalf of end users in practical settings, from digital shopping assistants to next-g
arXiv:2601.23206v2 Announce Type: replace Abstract: Large language models (LLMs) offer promise for dynamic game content generation, but they face critical barriers, including narrative incoherence and
arXiv:2605.19523v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have demonstrated remarkable proficiency in general multi-modal understanding; yet they struggle to efficiently acquire
arXiv:2605.18850v1 Announce Type: cross Abstract: We introduce KadiAssistant, a privacy-by-design AI assistant integrated into the Kadi research data ecosystem, enabling researchers to efficiently acc
arXiv:2605.20170v1 Announce Type: new Abstract: Modern Large Language Models (LLMs) have shown impressive performances in user-facing tasks such as question answering, as well as consistent improvemen
arXiv:2605.19416v1 Announce Type: new Abstract: Group Relative Policy Optimization(GRPO) has become a cornerstone of modern reinforcement learning alignment, prized for its efficacy in foregoing an ex
arXiv:2605.19008v1 Announce Type: new Abstract: Modern language-model training is increasingly exposed to instability, degraded runs, and wasted compute, especially under aggressive learning-rate, sca
arXiv:2605.19274v1 Announce Type: new Abstract: LLMs deployed multilingually are often audited via English explanations for non-English inputs. We evaluate extractive explanations ''where the model id
arXiv:2605.19723v1 Announce Type: cross Abstract: Mathematical reasoning is essential for problem-solving in education, science, and industry, serving as a crucial benchmark for evaluating artificial
arXiv:2605.18869v1 Announce Type: cross Abstract: Large language models (LLMs) achieve strong performance across a wide range of tasks but are highly sensitive to prompt design, motivating the need fo
arXiv:2605.18956v1 Announce Type: new Abstract: Recent motion-language models unify tasks like comprehension and generation but operate at a coarse granularity, lacking fine-grained understanding and
arXiv:2605.18884v1 Announce Type: cross Abstract: Multimodal emotion recognition aims to integrate text, audio, and video sources to understand human affective states. Although multimodal large langua
arXiv:2605.20098v1 Announce Type: new Abstract: Claim verification is an important problem in high-stakes settings, including health and finance. When information underpinning claims is incomplete or
New course: Build AI agents that generate images and videos -- an under-explored frontier. A key to performance is having the agent evaluate its own output, and iterate to improve quality. This short
arXiv:2605.19769v1 Announce Type: new Abstract: We present OpenComputer, a verifier-grounded framework for constructing verifiable software worlds for computer-use agents. OpenComputer integrates four
arXiv:2605.19351v1 Announce Type: cross Abstract: Generative agents based on large language models reproduce believable human behavior in cooperative settings, but how they should reason in situations
arXiv:2605.19514v1 Announce Type: new Abstract: Many works make the eye-catching claim that Transformers are Turing-complete. However, the literature often conflates two distinct settings: (i) a fixed
arXiv:2605.18832v1 Announce Type: cross Abstract: The Transformer is the foundational building block of modern AI, yet offers no principled handling of uncertainty, which is prevalent in real applicat
arXiv:2605.19173v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly explored for clinical decision support, yet most evaluations are conducted in English, leaving their relia
arXiv:2605.19976v1 Announce Type: new Abstract: Visual planning asks a model to generate the remaining steps of a procedure in natural language given a partial video context and a goal. Progress on th
arXiv:2605.19282v1 Announce Type: new Abstract: Muon is a matrix-aware optimizer that leverages Newton-Schulz (NS) iterations to enforce spectral gradient orthogonalization by driving all singular val
arXiv:2602.04663v2 Announce Type: replace-cross Abstract: Reinforcement learning has been widely applied to diffusion and flow models for visual tasks such as text-to-image generation. However, these
arXiv:2605.19344v1 Announce Type: new Abstract: Linguistic cues such as 'I believe' and 'probably' offer an intuitive interface for communicating confidence, yet a generalisable, principled calibratio
arXiv:2605.19095v1 Announce Type: cross Abstract: Schedule-Free Learning has shown promise as a practical anytime training method for machine learning, showing success across dozens of standard benchm
arXiv:2605.19357v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly applied to scientific research, yet existing evaluations often fail to reflect the fine-grained capabiliti
arXiv:2605.18765v1 Announce Type: cross Abstract: To augment Large Language Models (LLMs) for multi-hop question answering, a mainstream solution within Graph Retrieval Augmented Generation (GraphRAG)
arXiv:2605.19561v1 Announce Type: cross Abstract: As Large Language Models (LLMs) advance toward practical deployment, the Microscaling FP4 (MXFP4) format has emerged as a cornerstone for next-generat
arXiv:2605.19064v1 Announce Type: cross Abstract: Workforce transformations are difficult to forecast and costly to mismanage. In particular, the integration of artificial intelligence into knowledge
arXiv:2512.18552v2 Announce Type: replace-cross Abstract: While current software agents powered by large language models (LLMs) and agentic reinforcement learning (RL) can boost programmer productivit
arXiv:2605.20086v1 Announce Type: cross Abstract: Recent work pairs LLMs with evolutionary search to iteratively generate, modify, and select code using task-specific feedback. These systems have prod
arXiv:2605.17380v1 Announce Type: new Abstract: We present the Agentic AI Detection and Response (ADR) system, the first large-scale, production-proven enterprise framework for securing AI agents oper