Knowledge catalogue
arXiv:2509.15549v2 Announce Type: replace Abstract: Multilingual instruction fine-tuning (IFT) empowers large language models to generalize across diverse linguistic and cultural contexts; however, hi
arXiv:2604.26973v1 Announce Type: cross Abstract: Multiobjective optimization remains challenging for many scientific and engineering problems due to the need to balance convergence, diversity, and co
Francois Chollet shared a blog post analyzing failure modes of frontier AI models, specifically examining performance on the ARC (Abstraction and Reasoning Corpus) AGI benchmark with models including
arXiv:2604.28167v1 Announce Type: cross Abstract: In this study, we use machine learning to classify and interpolate the phase structure of the Vicsek flocking model across the three-dimensional param
arXiv:2604.27618v1 Announce Type: new Abstract: To enhance LLMs' impact on math education, we need data on their mathematical prowess and biases across prompts. To fill this gap, we introduce MEDS (Ma
arXiv:2604.27819v1 Announce Type: new Abstract: Multi-server MCP agents create an information-flow control problem: faithful tool composition can turn individually benign read/write permissions into c
arXiv:2604.27374v1 Announce Type: new Abstract: As LLMs become credible readers of earnings calls, investor-relations Q&A, guidance, and disclosure language, supervised financial NLP benchmarks increa
arXiv:2604.27393v1 Announce Type: new Abstract: Recent progress in multimodal large language models (MLLMs) has brought AI capabilities from static offline data processing to real-time streaming inter
arXiv:2604.28031v1 Announce Type: new Abstract: When researchers iteratively refine ideas with large language models, do the models preserve fidelity to the original objective? We introduce DriftBench
arXiv:2604.26984v1 Announce Type: new Abstract: Representational collapse, where embeddings become anisotropic and lose multi-scale structure, can erode downstream performance long before performance
arXiv:2504.02768v4 Announce Type: replace Abstract: We introduce MultiBLiMP 1.0, a massively multilingual benchmark of linguistic minimal pairs, covering 101 languages and 2 types of subject-verb agre
arXiv:2602.20122v2 Announce Type: replace-cross Abstract: How do large language models (LLMs) know what they know? Answering this question has been difficult because pre-training data is often a 'blac
arXiv:2510.18183v2 Announce Type: replace Abstract: Finding Nash equilibria in two-player zero-sum imperfect-information games remains a central challenge in multi-agent reinforcement learning. Recent
arXiv:2604.27852v1 Announce Type: cross Abstract: Although precise recall is a core objective in Retrieval-Augmented Generation (RAG), a critical oversight persists in the field: improvements in retri
arXiv:2604.27820v1 Announce Type: new Abstract: Every document format in existence was designed for a human reader moving linearly through text. Autonomous LLM agents do not read - they retrieve. This
📢 Official Announcement: Qwen Partners with Fireworks AI to Accelerate Access to Qwen Family Models We are pleased to announce a strategic partnership between Qwen and Fireworks AI to deliver optimize
On 5/5 @realDanFu and team will discuss DSV4’s hybrid attention and KV cache efficiency, should be a great session! Join us Tue 5/5: #DeepSeek-V4's hybrid attention + sparse MoE reduces KV cache up to
Once again IP thieves accusing other IP thieves of IP thievery! The nerve! @ChrisRMcGuire Anthropic claimed OpenAI violated their terms of service by using their API (I suspect they would call it “dis
One week since the launch of GPT-5.5, and it’s already our strongest model launch yet. API revenue is growing more than 2x faster than any prior release, while Codex doubled revenue in under seven day
arXiv:2504.15564v3 Announce Type: replace-cross Abstract: Existing class-level code generation datasets are either synthetic (ClassEval: 100 classes) or insufficient in scale for modern training needs
arXiv:2506.22500v2 Announce Type: replace-cross Abstract: Automated identification of surgical safety risks is critical for improving patient outcomes; however, Multimodal Large Language Models (MLLMs
arXiv:2506.08332v3 Announce Type: replace Abstract: Machine learning has been widely used to optimize complex engineering workflows across numerous domains. In integrated circuit design, modern flows
Our CEO @jerryjliu0 in @VentureBeat , on what's actually changing in the LLM stack: 'We've really identified that there's a core set of data that has been locked up in all these file format containers
arXiv:2604.27870v1 Announce Type: new Abstract: Convolutional Neural Networks (CNNs) are widely assumed to be translation-invariant, yet standard architectures exhibit a startling fragility: even a si
arXiv:2604.26991v1 Announce Type: cross Abstract: Recent advances in data-centric medical AI have produced highly accurate diagnostic systems, but the emphasis on data curation and performance metrics
arXiv:2604.27401v1 Announce Type: new Abstract: Perturbation probing generates task-specific causal hypotheses for FFN neurons in large language models using two forward passes per prompt and no backp
arXiv:2604.28169v1 Announce Type: cross Abstract: Modern video diffusion models excel at appearance synthesis but still struggle with physical consistency: objects drift, collisions lack realistic reb
arXiv:2604.27911v1 Announce Type: new Abstract: Foundation models are deep neural networks (such as GPT-5, Gemini~3, and Opus~4) trained on large datasets that can perform diverse downstream tasks --
arXiv:2604.27796v1 Announce Type: new Abstract: Exponential growth in the scale of modern foundation models has led to the widespread adoption of Low-Rank Adaptation (LoRA) as a parameter-efficient fi
arXiv:2604.27279v1 Announce Type: cross Abstract: Audio-based stuttering systems to date have been trained for detection -- what disfluency is present now -- leaving prediction, the capability needed
arXiv:2604.28123v1 Announce Type: cross Abstract: The standard post-training recipe for large multimodal models (LMMs) applies supervised fine-tuning (SFT) on curated demonstrations followed by reinfo
arXiv:2602.07408v2 Announce Type: replace Abstract: Predicting gene regulation responses to biological perturbations requires reasoning about underlying biological causalities. While large language mo
arXiv:2512.07703v2 Announce Type: replace Abstract: Large foundation models have emerged in the last years and are pushing performance boundaries for a variety of tasks. Training or even finetuning su
arXiv:2604.27319v1 Announce Type: cross Abstract: Large Language Models (LLMs) have achieved remarkable progress in recent years, driving their adoption across a wide range of domains, including compu
arXiv:2509.09513v2 Announce Type: replace-cross Abstract: Biophysical diffusion MRI models like Neurite Exchange Imaging (NEXI) are essential for probing gray matter microstructure, estimating compart
arXiv:2604.27233v1 Announce Type: new Abstract: Tool-calling agents are evaluated on tool selection, parameter accuracy, and scope recognition, yet LLM trajectory assessments remain inherently post-ho
arXiv:2604.27323v1 Announce Type: cross Abstract: Hyperspectral image (HSI) and SAR/LiDAR data offer complementary spectral and structural information for land-cover classification. However, their eff
Dan Goodin / Ars Technica: Researchers detail CopyFail, a now-patched Linux vulnerability that lets unprivileged users gain admin access, as many distributions have yet to add fixes — Publicly release
arXiv:2604.27559v1 Announce Type: cross Abstract: Radiology report generation (RRG) has emerged as a promising approach to alleviate radiologists' workload and reduce human errors by automatically gen
RL is a bit of a double edged sword: in known territory performance increases, but in unknown territory the model tends to hallucinate that it is performing a completely different task it was trained
arXiv:2604.27616v1 Announce Type: new Abstract: People commonly leverage structured content to accelerate knowledge acquisition and research problem solving. Among these, roadmaps guide researchers th
SpaceX's Falcon Heavy returned to flight this week, marking its first mission of 2026 by launching a heavy-lift payload for the US Space Force. Russia's Soyuz-5 rocket lifted off on April 30 from Baik
arXiv:2601.14289v2 Announce Type: replace-cross Abstract: Understanding research papers remains challenging for foundation models due to specialized scientific discourse and complex figures and tables
arXiv:2604.27780v1 Announce Type: cross Abstract: Large Language Models (LLMs) have rapidly improved in performance across code-related tasks, making their integration into Register Transfer Level (RT
arXiv:2604.27025v1 Announce Type: cross Abstract: Automatic feature engineering is an effective approach for improving predictive performance in tabular learning. However, expand-and-reduce methods, s
arXiv:2408.13122v2 Announce Type: replace-cross Abstract: The Variational Bayesian method (VB) is used to solve the probability distributions of latent variables with the minimum free energy criterion
arXiv:2604.26957v1 Announce Type: cross Abstract: In science education, students frequently construct hand-drawn visual models of scientific phenomena. These drawings rely on a visual structure where
arXiv:2604.27488v1 Announce Type: new Abstract: We introduce Skills-Coach, a novel automated framework designed to significantly enhance the self-evolution of skills within Large Language Model (LLM)-
arXiv:2604.27437v1 Announce Type: new Abstract: 3D Gaussian Splatting (3D GS) is widely adopted for novel view synthesis due to its high training and rendering efficiency. However, its efficiency reli
arXiv:2604.27555v1 Announce Type: new Abstract: Automatically generating interactive 3D indoor scenes from natural language is crucial for virtual reality, gaming, and embodied AI. However, existing L
arXiv:2604.27326v1 Announce Type: cross Abstract: Hyperspectral image super-resolution is essential for enhancing the spatial fidelity of HSI data, yet existing deep learning methods often struggle wi
arXiv:2604.28039v1 Announce Type: new Abstract: Spectra are a prevalent yet highly information-dense form of scientific imagery, presenting substantial challenges to multimodal large language models (
arXiv:2604.27368v1 Announce Type: new Abstract: Statistical inference in observational science typically relies on a fundamental assumption: as sample size increases and uncertainties decrease, the in
arXiv:2604.26993v1 Announce Type: cross Abstract: We study gradient descent for rank-1 matrix factorization through a certificate-based viewpoint. The central object is a parameterized quadratic certi
arXiv:2604.27151v1 Announce Type: new Abstract: Computer-use agents provide a promising path toward general software automation because they can interact directly with arbitrary graphical user interfa
arXiv:2604.27232v1 Announce Type: new Abstract: Models of sign language have historically lagged behind those for spoken language (text and speech). Recent work has greatly improved their performance
arXiv:2509.05753v2 Announce Type: replace-cross Abstract: The rise of synthetic media has blurred the boundary between reality and fabrication under the evolving power of artificial intelligence, fuel
arXiv:2601.20969v3 Announce Type: replace Abstract: Epistemic planning extends (multi-agent) automated planning by making agents' knowledge and beliefs first-class aspects of the planning formalism. O
arXiv:2604.26954v1 Announce Type: cross Abstract: Strategic model selection and reasoning settings are more effective than ensembling for optimizing automated scoring with large language models (LLMs)
arXiv:2604.27274v1 Announce Type: new Abstract: As AI transitions toward multi-agent systems (MAS) to solve complex workflows, research paradigms operate on the axiomatic assumption that agent collabo