Knowledge catalogue
arXiv:2604.26340v1 Announce Type: new Abstract: LoRA-MoE has emerged as an effective paradigm for parameter-efficient fine-tuning, combining the low training cost of LoRA with the increased adaptation
arXiv:2604.26382v1 Announce Type: cross Abstract: Most enterprise document AI today is a pipeline. Parse, index, retrieve, generate. Each of those stages has been studied to death on its own -- what's
arXiv:2512.08982v2 Announce Type: replace-cross Abstract: Retinex-based low-light image enhancement benefits from separating reflectance and illumination, yet recent generative approaches often rely o
arXiv:2604.26632v1 Announce Type: cross Abstract: We propose a dual-channel reservoir-computing scheme for inferring the dynamics of two distinct chaotic systems with a single machine. By augmenting a
// OCR-Memory // Well this is a unique approach to store memory for long-horizon agents. Most of the agent memory systems compress trajectories into text summaries and hope the model remembers what ma
arXiv:2603.15262v2 Announce Type: replace Abstract: Modern e-commerce search is evolving to resolve complex user intents. While Large Language Models (LLMs) offer strong reasoning, existing LLM-based
arXiv:2604.26897v1 Announce Type: new Abstract: Origami-inspired robotic grippers have shown promising potential for object manipulation tasks due to their compact volume and mechanical flexibility. H
arXiv:2604.26247v1 Announce Type: cross Abstract: Multimodal recommendation improves user modeling by integrating collaborative signals with heterogeneous item content. In real applications, user inte
arXiv:2604.26839v1 Announce Type: new Abstract: Assisting humans in open-world outdoor environments requires robots to translate high-level natural-language intentions into safe, long-horizon, and soc
arXiv:2604.25176v1 Announce Type: new Abstract: The digitization of multi-domain retail billing documents remains a challenging task due to variability in scan quality, layout heterogeneity, and domai
arXiv:2604.25376v1 Announce Type: new Abstract: Accurate brain lesion segmentation in MRI is vital for effective clinical diagnosis and treatment planning. Due to high annotation costs and strict data
arXiv:2604.25481v1 Announce Type: cross Abstract: We introduce a Hopfield-type associative memory in which effective connectivity is multiplicatively modulated by astrocytic gains evolving under an en
arXiv:2604.24765v1 Announce Type: cross Abstract: P300-based brain-computer interfaces (BCIs) are widely used for communication, but population heterogeneity may alter the neural patterns available fo
arXiv:2604.24809v1 Announce Type: new Abstract: We present Nautile-370M, a 371-million-parameter small language model designed for efficient reasoning under strict parameter and inference budgets. Nau
arXiv:2604.25448v1 Announce Type: new Abstract: Navigating AI regulation across jurisdictions is increasingly difficult for policymakers, legal professionals, and researchers. To address this, we pres
arXiv:2604.25028v1 Announce Type: new Abstract: Recent work revisiting measurability in the fundamental theorem of statistical learning imposes Borel measurability of ghost-gap suprema. We show that,
arXiv:2604.04973v2 Announce Type: replace-cross Abstract: This paper presents StrADiff, a Structured Source-Wise Adaptive Diffusion Framework for unsupervised blind source separation under linear and
arXiv:2603.19124v2 Announce Type: replace Abstract: This paper presents the design, modeling, and fabrication of 3D-printed, tendon-actuated continuum robots featuring a flexible, tapered backbone con
We’re excited to introduce KAME: Tandem Architecture for Enhancing Knowledge in Real-Time Speech-to-Speech Conversational AI, accepted at #ICASSP2026! 🐢 Blog https://pub.sakana.ai/kame/ Paper https://
arXiv:2604.23388v1 Announce Type: cross Abstract: Generative information retrieval (GenIR) consolidates retrieval into a single neural model that decodes document identifiers (docids) directly from qu
arXiv:2512.03915v3 Announce Type: replace-cross Abstract: In large-scale AI training, Sparse Mixture-of-Experts (s-MoE) layers enable scaling by activating only a small subset of experts per token. An
arXiv:2604.24559v1 Announce Type: cross Abstract: Chart-to-code generation converts a chart image into an executable plotting script, enabling faithful reproduction and editable visualizations. Existi
arXiv:2604.23345v1 Announce Type: new Abstract: Cross-domain task-oriented dialogue requires reasoning over implicit and explicit feasibility constraints while planning long-horizon, multi-turn action
arXiv:2604.22820v1 Announce Type: cross Abstract: Long-horizon tool-using tasks sometimes benefit from revisiting earlier subtasks for recovery and exploration, but added multi-agent workflow flexibil
arXiv:2604.23952v1 Announce Type: cross Abstract: Stochastic reduced-order models are widely used to represent the effective dynamics of complex systems, but estimating their drift and diffusion coeff
arXiv:2604.24170v1 Announce Type: new Abstract: Concept Bottleneck Models (CBMs) predict through human-interpretable concepts, but they typically output point concept probabilities that conflate epist
arXiv:2604.23693v1 Announce Type: new Abstract: Heterogeneous multi-robot systems feature significant adaptability for complex environments. However, effective collaboration that fully exploits the ro
arXiv:2511.22177v2 Announce Type: replace-cross Abstract: Most post-training methods for text-to-image samplers focus on model weights: either fine-tuning the backbone for alignment or distilling it f
arXiv:2604.23763v1 Announce Type: new Abstract: Large diffusion transformers (DiTs) follow global editing instructions well but consistently leak local edits into unrelated regions, because joint-atte
arXiv:2604.24563v1 Announce Type: cross Abstract: Machine-learning interatomic potentials (MLIPs) have enabled molecular dynamics at near ab initio accuracy, yet remain limited to energies and forces
arXiv:2604.23588v1 Announce Type: new Abstract: Financial AI systems must produce answers grounded in specific regulatory filings, yet current LLMs fabricate metrics, invent citations, and miscalculat
arXiv:2602.15846v2 Announce Type: replace Abstract: Decoder-only large language models achieve strong broad performance but are brittle to minor grammatical perturbations, undermining reliability for
arXiv:2604.23903v1 Announce Type: cross Abstract: Large-scale neuroscience is generating rich datasets across animals, brain areas and behavioral contexts, yet our modeling efforts remains fragmented
arXiv:2604.23108v1 Announce Type: cross Abstract: Large Language Models (LLMs) based on Mixture-of-Experts (MoE) are pivotal in industrial applications for their ability to scale performance efficient
arXiv:2604.23620v1 Announce Type: new Abstract: We present Move-Then-Operate, a Vision language action framework that explicitly decouples robotic manipulation into two distinct behavioral phases: coa
arXiv:2604.24674v1 Announce Type: new Abstract: Radar offers unique advantages for localization in unstructured environments, including robustness to weather, lighting, and airborne particulates. Whil
arXiv:2604.23804v1 Announce Type: new Abstract: We generalise the reparameterization trick applied in variational autoencoders (VAEs) letting these have latent spaces of non-trivial topology - i.e. th
arXiv:2604.22967v1 Announce Type: cross Abstract: Trust Region Bayesian Optimization (TuRBO) is an effective strategy for alleviating the curse of dimensionality in high-dimensional black-box optimiza
arXiv:2604.24514v1 Announce Type: new Abstract: Accurate trajectory prediction is fundamentally challenging due to high scene heterogeneity - the severe variance in motion velocity, spatial density, a
arXiv:2601.03555v2 Announce Type: replace Abstract: Training reliable tool-augmented agents remains a significant challenge, largely due to the difficulty of credit assignment in multi-step reasoning.
arXiv:2509.00747v2 Announce Type: replace-cross Abstract: Learning with physical systems is an emerging paradigm that seeks to harness the intrinsic nonlinear dynamics of physical substrates for learn
arXiv:2604.24380v1 Announce Type: new Abstract: While Large Vision Language Models (LVLMs) demonstrate impressive capabilities, their substantial computational and memory requirements pose deployment
arXiv:2604.23806v1 Announce Type: cross Abstract: The reverse process in score-based diffusion models is formally equivalent to overdamped Langevin dynamics in a time-dependent energy landscape. In ou
arXiv:2604.23080v1 Announce Type: cross Abstract: Large-scale agentic systems run on distributed infrastructures where many software agents share physical hosts and are discovered via peer-to-peer mec
arXiv:2604.23878v1 Announce Type: new Abstract: Despite a century of empirical memory research, existing AI agent memory systems rely on system-engineering metaphors (virtual-memory paging, flat LLM s
arXiv:2602.11931v2 Announce Type: replace-cross Abstract: Evolutionary agentic systems intensify the trade-off between computational efficiency and reasoning capability by repeatedly invoking large la
Don't try to build a self-improving AI agent without evals. You are just wasting time and compute. An agent can't improve from traces it can't evaluate. This is why it's exciting to see @FutureAGI_ go
arXiv:2505.14351v4 Announce Type: replace-cross Abstract: Tibetan is a low-resource language with minimal parallel speech corpora spanning its three major dialects-U-Tsang, Amdo, and Kham-limiting pro
arXiv:2604.21952v1 Announce Type: cross Abstract: This work presents a multi-layered methodology for efficiently accelerating multimodal foundation models (MFMs). It combines hardware and software co-
arXiv:2503.21435v3 Announce Type: replace Abstract: Recent advances in Vision-Language Models (VLMs) have shown promising capabilities in interpreting visualized graph data, offering a new perspective
How do AI Agents spend your money? Most teams treat agent token costs as a rounding error even though the data says they shouldn't. New paper presents the first systematic study of how agents actually
arXiv:2604.22081v1 Announce Type: new Abstract: Most reinforcement-learning (RL) controllers used in continuous control are architecturally centralized: observations are compressed into a single laten
Keras Kinetic has a new alpha release: v0.0.2! Including a new docs website: http://kinetic.readthedocs.io Kinetic is my favorite new release from the Keras team: a super simple Modal-like API to run
KITT is real Any new Tesla can do this FSD drove my wife and I all the way from San Diego to Palm Springs for the weekend. Today it gave us an architectural tour powered by @grok . It picked the homes
arXiv:2604.22405v1 Announce Type: new Abstract: K-plane clustering (KPC), hyperplane clustering, and mixture regression all essentially fall within the same class of problems. This problem can be conc
arXiv:2604.22134v1 Announce Type: new Abstract: Large Language Models (LLMs) have been widely explored in educational scenarios. We identify a critical vulnerability in current educational LLMs, pedag
arXiv:2604.22072v1 Announce Type: cross Abstract: Federated learning (FL) aggregation on serverless platforms faces a hard scalability ceiling: existing architectures (lambda-FL, LIFL) partition clien
The Japanese railway privatization of 1987 stands as one of the most devastating defeats ever dealt to statist transportation mythology. The government split the bloated Japan National Railways into s
What if instead of building one giant AI, we evolved a coordinator to orchestrate a diverse team of specialized AIs? 🐟 Excited to share our new paper: “TRINITY: An Evolved LLM Coordinator”, published
Whoah, self-driving cars compete with airlines. I never considered that till now. Yesterday I drove my @tesla 900 miles on FSD from Miami to Nashville and I realized it’s genuinely the better option.