Knowledge catalogue
arXiv:2606.16794v2 Announce Type: replace Abstract: This study proposes a domain-specific LLM-based Visual Explanation Evaluation Framework for assessing visual attention explanations in facial skin d
arXiv:2603.12572v5 Announce Type: replace Abstract: Memory embeddings are crucial for memory-augmented systems, such as OpenClaw, but their evaluation is underexplored in current text embedding benchm
arXiv:2607.22381v1 Announce Type: new Abstract: Curvature notions on graphs, particularly Ollivier-Ricci and Forman, have emerged as powerful tools for addressing fundamental issues in Graph Neural Ne
love this frame. calls to mind the role of the hippocampus in human navigation (via place cells and grid cells), and how navigation is, in a sense, what makes agents *agents* vs plain old LLM calls in
arXiv:2607.21998v1 Announce Type: new Abstract: This paper introduces a new benchmark test, Medical-Checklist, for assessing medical multimodal models. The recent advancements in multimodal models hav
New York Times: Microsoft introduces MAI-Cyber-1-Flash, an AI model trained for cybersecurity, and launches Perception, an agentic security system to patch vulnerabilities — As some executives fret ov
The National Oceanic and Atmospheric Administration (NOAA) is embarking on a transformative journey to redefine how we understand and predict patterns in the Earth’s atmosphere that affect the weather
arXiv:2607.21978v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) architectures have been widely adopted in large language models, yet parameter-efficient fine-tuning (PEFT) for MoE models rema
moonshotai/Kimi-K3 As promised earlier this month, Moonshot have released the weights for their excellent 2.8 trillion parameter Kimi K3. They're a hefty 1.56TB on Hugging Face. Kimi introduced their
arXiv:2607.21671v1 Announce Type: new Abstract: Neural network compression and interpretability remain open challenges in modern deep learn- ing, where billion-parameter architectures deliver impressi
Nexus connects to the agentic harnesses your teams already use, whether that’s Claude Code, Codex, OpenCode, or your own custom tooling. It gives you: → Intelligent routing, automatically matching eac
Nice little insights on doing autoresearch with coding agents. Hand a coding agent a dataset, an eval script, one editable file, and no supervision. That's autoresearch and it tries to optimize the nu
I just managed to get it running on windows and this thing is fucking insane. I get around 550-720t/s depending on task at hand. Previously to get to such numbers i would have to do batching and agent
NVIDIA’s Nemotron 3 Ultra, when paired with the ACE‑RTL agent, achieves a 97.1 % average pass rate on the CVDP benchmark across nine RTL task categories—surpassing GLM 5.2 and Kimi K2.6 while using up
arXiv:2507.18036v2 Announce Type: replace-cross Abstract: Securing intellectual property (IP) in Machine Learning as a Service is critical yet challenging. While deep neural network watermarking serve
arXiv:2607.22226v1 Announce Type: new Abstract: Foundation-model-based vision-language navigation (VLN) has advanced autonomous robot navigation by enabling robots to interpret natural-language instru
On FrontierCode 1.1 Extended, our benchmark for real-world engineering tasks that grades mergeability and quality, Kimi K3 scores 58.2% with a 63.6% pass rate. Within Devin, it excels on reproducing b
arXiv:2607.22119v1 Announce Type: cross Abstract: Multi-stream robot manipulation policies achieve unparalleled sample efficiency and generalization by modeling actions relative to environmental refer
arXiv:2607.22513v1 Announce Type: cross Abstract: Commercial large language models are increasingly used as knowledge references, yet their stance on contested scientific claims is neither stable nor
arXiv:2601.12291v2 Announce Type: replace-cross Abstract: Scalable and maintainable maps are fundamental to large-scale navigation and the long-term deployment of robots in real-world environments. Ho
arXiv:2607.14193v2 Announce Type: replace-cross Abstract: The Helmholtz equation governs time-harmonic wave propagation, and in dissipative media a complex modulus renders its squared wavenumber kappa
arXiv:2607.22486v1 Announce Type: new Abstract: Control valve stiction is a common cause of unwanted oscillations and poor control-loop performance in industrial processes. Data-driven methods can aut
arXiv:2607.22238v1 Announce Type: new Abstract: Bayesian optimization (BO) is an optimization method that sequentially proposes the next candidate explainable variables for optimizing target variables
arXiv:2607.21752v1 Announce Type: new Abstract: Data-adaptive sparse attention masks substantially outperform fixed patterns (e.g., BigBird and Longformer) and can even exceed dense attention on long
arXiv:2607.21672v1 Announce Type: cross Abstract: Long source-code contexts consume many text tokens, motivating the proposal to render code as images for vision-language models. Recent work asks whet
arXiv:2606.14022v2 Announce Type: replace Abstract: LayerNorm-based GNNs routinely erase the topology signals (degree, centrality, k-core) that node-selection policies should depend on, but the litera
arXiv:2607.21612v1 Announce Type: cross Abstract: Parameter-efficient fine-tuning methods like LoRA have become the default for adapting large language models, succeeding across instruction following,
arXiv:2607.21995v1 Announce Type: cross Abstract: Rare-regime discovery in parameterized dynamical systems is an active-search problem: find one verified parameter at which a scientifically defined qu
arXiv:2607.21637v1 Announce Type: new Abstract: This paper explores the efficacy of quasi-Monte Carlo (QMC) weight initialization for meta-reinforcement learning within modern benchmark environments.
I finished the speed leg of my spec-decode benchmarking for Qwen3.6-27B, main algorithms across quants. Overall: the heavier the quant, the more spec-decode buys you (10 of 10 speculative configs rank
arXiv:2607.22293v1 Announce Type: new Abstract: Medical multimodal large language models (MLLMs) are increasingly expected to perform complex image understanding tasks, yet their reliability is often
arXiv:2607.22071v1 Announce Type: new Abstract: With the development of precision livestock farming and the advances in computer vision, visual animal biometrics has gained attention. Using biometric
Releasing the model weights and technical report of Kimi K3. Kimi K3 is our most capable model: a 2.8T MoE model with native visual understanding and a 1M-token context window. New model architecture:
arXiv:2607.21973v1 Announce Type: new Abstract: Vision foundation models are increasingly reused as frozen backbones for downstream visual recognition, making parameter-efficient adaptation a central
arXiv:2607.21787v1 Announce Type: new Abstract: Medical ultrasound (US) image segmentation faces significant challenges due to speckle noise, low-contrast boundaries, acoustic shadowing, and acquisiti
arXiv:2607.21866v1 Announce Type: new Abstract: Prior classical-ML learning-curve work fits power laws to tree, linear, and kernel models on tabular data, but at small scale: typically one curve, one
arXiv:2607.22393v1 Announce Type: cross Abstract: Vision-language model (VLM) agents increasingly use tools to act on 3D scenes rather than only describe them. Existing 3D benchmarks score textual res
arXiv:2607.21610v1 Announce Type: cross Abstract: Schema graphs are an upstream bottleneck of schema-grounded information extraction and knowledge graph construction, yet most extraction systems assum
arXiv:2607.21855v1 Announce Type: new Abstract: We investigate whether symbolic regression can discover explicit neural network weight-update rules that outperform standard hand-designed optimizers on
arXiv:2607.22529v1 Announce Type: new Abstract: LLM training is shifting from manual design and annotation to interaction-driven self-evolution. However, existing self-evolutionary methods face a fund
Running local models means every token counts — an 8K or 16K window fills up fast when you're stuffing graph context into prompts for RAG. I benchmarked 10 graph serialization formats (JSON, GraphML,
arXiv:2505.00473v2 Announce Type: replace Abstract: We explore the promising performance of a transformer model in predicting outputs of parametric dynamical systems with external time-varying input s
arXiv:2607.21607v1 Announce Type: cross Abstract: Graph Neural Networks propagate information through local message passing, but the graph topologies themselves can silently prevent any amount of trai
arXiv:2607.11204v2 Announce Type: replace Abstract: Onboard quadruped inspection systems often share limited compute between perception and navigation, reducing the rate at which event-triggered contr
arXiv:2601.08160v2 Announce Type: replace Abstract: Agentic memory systems have become critical for enabling LLM agents to maintain long-term context and retrieve relevant information efficiently. How
arXiv:2607.22304v1 Announce Type: new Abstract: Synthetic data augmentation in speech is common practice for linguistic tasks like ASR, but has seen far less work for paralinguistic ones, especially c
arXiv:2512.15423v2 Announce Type: replace Abstract: Monocular depth foundation models achieve remarkable generalization by learning large-scale semantic priors, but this creates a critical vulnerabili
arXiv:2607.21613v1 Announce Type: cross Abstract: We investigate where and how transformer-based language models commit to predictions in multiple-choice question answering. We identify the _Hard Deci
The LangChain podcast where @hwchase17 interviews agent builders is full of alpha. Recent one with @EnoReyes was the best one yet. Sharing my unstructured notes: Eno keeps bringing back some core conc
arXiv:2607.22077v1 Announce Type: cross Abstract: Single-pixel sensing encodes a scene as a short sequence of coded measurements, and image-free methods infer the task directly from that sequence. Rem
arXiv:2607.22352v1 Announce Type: new Abstract: We introduce time-reversed imaging, a new paradigm that infers what just happened in a scene from fading multimodal traces. Instead of extrapolating or
arXiv:2607.21644v1 Announce Type: new Abstract: We present a goal-agnostic control framework for partial differential equations (PDEs) built around a joint-embedding predictive architecture (JEPA). Th
arXiv:2607.21635v1 Announce Type: new Abstract: Personal agents maintain memories, learned skills, tool configurations, and policy state that evolve with each user. Existing agent benchmarks often eva
arXiv:2607.22201v1 Announce Type: cross Abstract: We introduce trajectory-regularized stochastic optimal control (TRSOC), which augments standard stochastic optimal control (SOC) with a Kullback--Leib
arXiv:2607.22149v1 Announce Type: new Abstract: Despite recent advances, self-supervised learning (SSL) models and Joint-Embedding Predictive Architectures (JEPAs) remain susceptible to learning spuri
arXiv:2607.22262v1 Announce Type: cross Abstract: Modeling shared and subject-specific structure in multisubject spatiotemporal data remains challenging, particularly in neuroimaging, where both spati
We are in a world where you can create truly unique, visually interesting and creative playable demos on demand with the current capabilities of Codex and Claude Code. We don't need to keep cloning th
We are releasing PerceptionBench, a benchmark that isolates visual perception and evaluates it as a set of atomic capabilities - discovered from how today's models fail, rather than defined in advance
Instead of 2T+ models, continuing to release highly capable small to medium size LLMs would really help to keep this community vibrant. Hardly anyone can even dream of running the recent 1.5-2T+ beast
We've open-sourced MoonEP, our high-performance communication library for distributed MoE workloads. Built to make expert-parallel communication more efficient at scale, MoonEP helps reduce communicat