Knowledge catalogue
arXiv:2605.24876v1 Announce Type: cross Abstract: We introduce a novel neural operator architecture designed to approximate solutions of linear elliptic partial differential equations with high-contra
arXiv:2605.23997v1 Announce Type: cross Abstract: Multimodal large language models via reinforcement learning (RL) have demonstrated remarkable capabilities in complex visual reasoning tasks, yet they
arXiv:2605.25469v1 Announce Type: new Abstract: Quantization-aware training (QAT) is widely deployed but typically relies on the Straight-Through Estimator (STE), which passes gradients through non-di
arXiv:2602.18527v2 Announce Type: replace-cross Abstract: Current audio-visual large language models (AV-LLMs) are predominantly restricted to 2D perception, relying on RGB video and monaural audio. T
arXiv:2605.24550v1 Announce Type: new Abstract: Fine-tuning-as-a-Service (FaaS) enables personalization of large language models (LLMs), but it can weaken safety-alignment under harmful fine-tuning at
arXiv:2602.17162v2 Announce Type: replace Abstract: Genomic Foundation Models (GFMs) typically rely on Masked Language Modeling (MLM) or Next-Token Prediction (NTP) to learn the 'Laws of Nature'. Whil
arXiv:2605.25916v1 Announce Type: new Abstract: Federated edge learning (FEEL) has recently emerged as a promising paradigm for achieving edge intelligence (EI) via enabling collaborative model traini
arXiv:2605.24414v1 Announce Type: new Abstract: We introduce JT-Safe-V2, a large language model designed to advance the safety and trustworthiness of foundation models, extending our previous JT-Safe
arXiv:2605.25240v1 Announce Type: cross Abstract: Two methodologies dominate current practices of benchmarking: rubric-based scoring evaluates items against predefined criteria, whereas comparative ju
Just built an insane new agent skill. It can perfectly extract slides from YT videos, then write notes, images, transcripts, and slides into Obsidian vaults. An HTML artifact allows me to navigate and
arXiv:2605.25163v1 Announce Type: cross Abstract: A panoramic X-ray compresses a 3D jaw into a 2D strip; we aim to recover the missing depth cleanly and fast. Existing implicit neural representations
arXiv:2510.02327v2 Announce Type: replace-cross Abstract: Real-time speech-to-speech (S2S) models excel at generating natural, low-latency conversational responses but often lack deep knowledge and se
arXiv:2605.25556v1 Announce Type: cross Abstract: Automated theorem proving systems built on Lean 4 increasingly rely on parallel tactic search over partially specified proofs, such as those generated
Brayden Lindrea / Cointelegraph: Kelp DAO says its restaked Ether token has been restored after a five-week recovery effort following a $293M exploit by North Korea's Lazarus Group on April 18 — Coint
arXiv:2510.01348v2 Announce Type: replace Abstract: Reliable long-range flight of unmanned aerial vehicles (UAVs) in GNSS-denied environments is challenging: integrating odometry leads to drift, loop
arXiv:2605.24647v1 Announce Type: new Abstract: Personalized dialogue requires more than recalling explicit user histories: systems also need to infer hidden user states that evolve through interactio
arXiv:2605.25284v1 Announce Type: new Abstract: User queries are often underspecified and may admit multiple valid interpretations. Rather than silently making assumptions about the user's intent, a h
arXiv:2605.25183v1 Announce Type: cross Abstract: Knowledge graph (KG) is an abstraction that can be extracted from text corpora and used for in-depth reasoning. Prior work has leveraged KGs to fine-t
arXiv:2605.24162v1 Announce Type: cross Abstract: Biological systems are governed by structured molecular interactions, where pathways, regulatory circuits, and functional gene relationships shape cel
arXiv:2605.22093v2 Announce Type: replace Abstract: Knowledge graphs have become the primary vehicle for data integration and are critical to the success of modern AI, but the diversity of KG modellin
arXiv:2502.06018v3 Announce Type: replace-cross Abstract: Although Kolmogorov-Arnold-based interpretable networks (KANs) possess strong theoretical expressiveness, they suffer from severe parameter ex
arXiv:2605.23933v1 Announce Type: cross Abstract: Educational Question Generation (EQG) aims to synthesize customized exercise questions that enhance student learning. An effective EQG system should i
arXiv:2605.25376v1 Announce Type: cross Abstract: Observability tells operators when an agent is slow. KYA tells operators when an agent is wrong, drifting, leaking, or quietly going rogue. We present
arXiv:2605.26040v1 Announce Type: new Abstract: Graph fraud detection has long depended on Graph Neural Networks (GNNs) to propagate and aggregate information across relational data. A critical obstac
arXiv:2605.25275v1 Announce Type: new Abstract: The Neural Tangent Kernel (NTK) framework explains optimization in over-parameterized neural networks via approximately linearized dynamics, yielding ex
arXiv:2605.24515v1 Announce Type: new Abstract: With climate change and increasing human pressure on natural landscapes, inland water resources are becoming progressively scarcer, more vulnerable, and
LangChain Academy Course: LangSmith Fleet Essentials Learn how to build your own agents with LangSmith Fleet. Anyone can now build, use, and manage an agent fleet for complex daily tasks, without writ
langsmith engine is an agent that helps you spin the optimization loop for your own agents everyone is talking about self-optimizing loops in software & agents. but what does that actually mean? in my
arXiv:2605.25036v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) extend large language models with visual understanding, but remain vulnerable to hallucination, where outputs are
arXiv:2605.26099v1 Announce Type: cross Abstract: Transformer-based large language models are increasingly used for long-horizon tasks; however, their attention mechanism scales poorly with context le
// Language Models Need Sleep // Let your agents 'sleep', folks. On a serious note, this is a fascinating paper on getting the most from long-horizon agents. Here is the problem with agents today: Att
arXiv:2602.02839v3 Announce Type: replace Abstract: Enabling robots to perform novel manipulation tasks from natural language instructions remains a fundamental challenge in robotics, despite signific
arXiv:2605.24584v1 Announce Type: cross Abstract: Fast linear algebra in deep learning usually comes with a choice: fixed geometry and exact computation, as in the Fourier transform, or adaptive geome
arXiv:2605.24981v1 Announce Type: new Abstract: Choosing a Large Language Model (LLM) for a given task requires comparing many strong candidates, yet standard evaluation relies on costly annotations o
last 4 days to submit talks: https://ai.engineer/cfp this is our first year featuring PREPRINT poster sessions for research papers as well - as @bclavie pointed out we need a separate process for this
arXiv:2605.25267v1 Announce Type: cross Abstract: Safe in-context reinforcement learning (ICRL) adapts online from interaction history without test-time parameter updates while controlling episode cos
arXiv:2605.25740v1 Announce Type: new Abstract: Offline goal-conditioned reinforcement learning (GCRL) provides a practical framework for obtaining goal-reaching policies from fixed datasets. However,
arXiv:2605.24608v1 Announce Type: new Abstract: We develop a rigorous algebraic framework for deep convolutional architectures, CNNs, ResNets, and encoder--decoder networks such as UNet, grounded in l
Launching our new paper on arXiv: we trained the largest multilingual food model ever built. 4.1M recipes. 7 languages. 1,790 ingredients. 300 dimensions. All of human cooking compressed into 2 megaby
arXiv:2605.24005v1 Announce Type: new Abstract: The evolution of Large Language Model (LLM) reasoning is bottlenecked by the scarcity of high-quality process data. While self-alignment via endogenous
arXiv:2503.19605v5 Announce Type: replace-cross Abstract: Understanding and certifying the generalization performance of machine learning algorithms -- i.e. obtaining theoretical estimates of the test
arXiv:2603.29123v2 Announce Type: replace Abstract: The next-token prediction (NTP) objective trains language models to predict a single token at each step, even though many continuations can express
arXiv:2605.24170v1 Announce Type: cross Abstract: Ordinary differential equation models of biochemical reactions are often formulated as stoichiometric systems in which the dynamics arise from a colle
arXiv:2411.09816v4 Announce Type: replace Abstract: Large neural networks achieve state-of-the-art performance on many tasks, yet their sheer size hinders deployment on resource-constrained devices. A
arXiv:2605.24931v1 Announce Type: new Abstract: Modern robotic policies increasingly rely on action chunking to execute complex tasks in the physical world. While action chunking improves temporal con
arXiv:2605.26012v1 Announce Type: cross Abstract: Deep reinforcement learning (RL) agents commonly rely on high-dimensional neural representations, despite growing evidence that task-relevant value an
arXiv:2605.24390v1 Announce Type: new Abstract: The eigendecomposition of the Laplace--Beltrami Operator (LBO) is fundamental to geometric analysis, yet computing its low-frequency eigenmodes remains
arXiv:2605.25581v1 Announce Type: new Abstract: Single-cell perturbation prediction aims to infer how cells respond to unseen interventions and to achieve out-of-distribution (OOD) generalization, pro
arXiv:2605.24985v1 Announce Type: cross Abstract: Limbless terrestrial animals exhibit exceptional locomotor versatility and control, currently unmatched by engineered counterparts. Here, we introduce
arXiv:2605.25383v1 Announce Type: cross Abstract: We consider graph diffusion processes constructed from finite i.i.d. samples drawn from an unknown manifold embedded in ambient Euclidean space, where
arXiv:2605.25551v1 Announce Type: new Abstract: Many learning problems require uncovering a hidden ordering that reveals structure in unordered data, such as monotonicity in sorting or spatial continu
arXiv:2605.23960v1 Announce Type: cross Abstract: Proteins encode diverse functions within complex three-dimensional structures, yet most deep learning representations remain highly entangled, obscuri
arXiv:2602.05052v3 Announce Type: replace Abstract: We present a unified algorithmic framework for the numerical solution, constrained optimization, and physics-informed learning of PDEs with a variat
arXiv:2605.25608v1 Announce Type: cross Abstract: The ability of deep neural networks to learn hierarchical features is widely regarded as a key mechanism underlying their success in high-dimensional
arXiv:2605.24597v1 Announce Type: new Abstract: Many applications of large language models (LLMs) require deductive reasoning, yet models frequently produce incorrect or redundant inference steps. We
arXiv:2605.25360v1 Announce Type: new Abstract: Large language models~(LLMs) are trained on heterogeneous multilingual corpora, yet existing policy optimization methods often implicitly restrict each
arXiv:2605.25720v1 Announce Type: new Abstract: Combinatorial generalization remains a central challenge in Deep Reinforcement Learning (DRL). Classical planning provides a simple yet challenging sett
arXiv:2511.12378v2 Announce Type: replace Abstract: Autonomous agents operating in sequential decision-making tasks under uncertainty can benefit from external action suggestions, which provide valuab
arXiv:2605.24881v1 Announce Type: new Abstract: Robotic surface-interaction tasks, such as spray painting or welding, require both accurate geometric planning and precise motion execution. While moder
arXiv:2605.25169v1 Announce Type: new Abstract: Public service programs often allocate limited resources under uncertainty about their benefits, creating a need for randomization to support credible e