Knowledge catalogue
FYI the engine's default kernel rules were measured on smaller chips (16/20-core M5s and a 32-core M4 Max), so a 40-core M5 Max runs guesses. Splash's repo includes a developer tool, “make tune-kernel
arXiv:2609.29836v1 Announce Type: new Abstract: While 2D Vision Foundation Models offer a pathway to automate 3D semantic pseudo-labelling, translating these priors into robust 3D representations typi
arXiv:2609.28713v1 Announce Type: cross Abstract: Self-supervised learning (SSL) countermeasures (CMs) have shown strong performance in recent years. However, they often show degraded performance whil
Spot on. 'When we got attacked, our team initially turned to frontier closed-source APIs that blocked us because of safeguards that still can’t always tell the difference between attackers and defende
arXiv:2609.29169v1 Announce Type: cross Abstract: We introduce Spot, Separate, and Enhance (SSE), the first multimodal, user-guided generative model for audio remixing and enhancement. SSE enhances vi
arXiv:2609.28502v1 Announce Type: new Abstract: Knowledge tracing (KT) models predict student performance opaquely, limiting pedagogical action. This study contributes a validation protocol testing pr
arXiv:2507.22170v2 Announce Type: replace-cross Abstract: Modern data analysis increasingly requires identifying shared latent structure across multiple high-dimensional datasets. A commonly used mode
arXiv:2609.29522v1 Announce Type: new Abstract: Tool-using language-model agents increasingly mutate schedulers, data pipelines, object stores, and access-control systems. Between an agent's read and
arXiv:2609.29549v1 Announce Type: new Abstract: Post-training pipelines must select one language-model policy from many checkpoints, prompts, and decoding rules. Mean evaluator scores can conceal rare
arXiv:2609.28543v1 Announce Type: cross Abstract: We analyze a simple stochastic inertial Krasnosel'skii--Mann (iKM) method for finding a fixed point of a nonexpansive operator in a real Hilbert space
arXiv:2609.29703v1 Announce Type: new Abstract: AI-agent evaluations usually inspect a final answer, yet error may enter through evidence, retrieval, prompting, generation or decision mapping. We intr
The volume of data being generated today brings both opportunity and massive operational complexity. Most teams that operate at scale don't discover issues until they appear on an invoice — and by the
arXiv:2609.29607v1 Announce Type: cross Abstract: While multimodal large language models (MLLMs) have advanced video understanding, they remain highly prone to hallucinations in dynamic scenes. We arg
arXiv:2609.28809v1 Announce Type: new Abstract: Mechanistic interpretability seeks to make verifiable statements about the internal behavior of large language models (LLMs). Many interpretability tech
arXiv:2609.28927v1 Announce Type: new Abstract: World action models (WAMs) that use future visual prediction at inference time incur substantial generation costs. Asynchronous execution reduces waitin
arXiv:2609.29912v1 Announce Type: cross Abstract: With the growing demand for privacy-preserving and occlusion-resilient human pose recognition (HPR), 5G channel state information (CSI) offers a promi
arXiv:2609.30048v1 Announce Type: new Abstract: If a language model can recognize code it wrote, it may favor that code as a judge, and instances of one model monitoring each other could collude. We t
arXiv:2609.29291v1 Announce Type: cross Abstract: We propose Sufficiently Reduced Distributional Regression (SRDR), a generative method that combines conditional distribution estimation with nonlinear
Super happy to release SmolDataEnvs: 5,000 verifiable RL environment tasks for hill-climbing small models in code and data science by @adithya_s_k 100% open source: environments, evals, training! http
arXiv:2609.29465v1 Announce Type: new Abstract: Large language model based coding agents have made substantial progress on repository-level software engineering tasks. Existing repository benchmarks,
TL;DR - Swift Flash is a killer model that massively reduces excess reasoning. Try it out! If you haven't seen from my previous comparison posts, I'm a huge fan of the Swift Qwen3.8 models. I've been
arXiv:2609.29814v1 Announce Type: new Abstract: Tabular foundation models (TFMs) provide a promising route to time-series classification, but their effectiveness depends on how sequential data are con
arXiv:2505.15465v2 Announce Type: replace Abstract: This paper introduces Synthetic Enclosed Echoes (SEE), a novel dataset designed to enhance robot perception and 3D reconstruction capabilities in un
arXiv:2609.30027v1 Announce Type: new Abstract: Frontier language models are rarely used in clinical workflows because the realistic, longitudinal benchmarks needed to develop them are scarce. Real el
arXiv:2609.29832v1 Announce Type: cross Abstract: A new method for multi-input flight maneuver design for system identification is presented. The method consists of injecting 'full-harmonic' orthogona
arXiv:2602.11700v2 Announce Type: replace-cross Abstract: Tabular prediction can benefit from in-table rows as few-shot evidence, yet existing tabular models typically perform instance-wise inference
arXiv:2609.28959v1 Announce Type: new Abstract: Humanoid parkour policies can traverse various terrains, but task completion may mask challenges of harsh landings, edge contacts, and unstable stance c
arXiv:2609.29131v1 Announce Type: cross Abstract: Internet texts are replete with format tags that carry structural, semantic, and functional meaning. Current large language model (LLM)-based translat
arXiv:2609.28590v1 Announce Type: cross Abstract: Background & Problem: Thyroid Fine-Needle Aspiration Biopsy (FNAB) cytology based on the Bethesda System plays a pivotal role in early thyroid cancer
arXiv:2609.28766v1 Announce Type: new Abstract: Applying adhesive tape to secure wire harnesses or seal packages requires robots to coordinate a flexible strip, a moving roll, and surfaces that attach
arXiv:2609.29499v1 Announce Type: new Abstract: Static pruning imposes one sparse structure on every prompt, even though reasoning, retrieval, generation, coding, and translation can depend on differe
arXiv:2609.29570v1 Announce Type: cross Abstract: Quantum reservoir computing (QRC) uses fixed quantum dynamics to encode a time series and trains only a classical readout, but a benchmark capacity al
arXiv:2609.28747v1 Announce Type: cross Abstract: A language model's confidence in an answer is often read as a proxy for how well it knows the corresponding fact. This manual documents an open toolki
arXiv:2609.29423v1 Announce Type: new Abstract: No two robots are truly identical: calibration, battery state, sensor drift and wear give every swarm a distribution of behaviour rather than a single p
arXiv:2609.29851v1 Announce Type: cross Abstract: Behavioural biometric templates are widely believed to degrade as the gap between enrolment and verification grows, but few studies measure this templ
arXiv:2609.30258v1 Announce Type: new Abstract: Distributed learning in embodied reinforcement-learning agents offers a degree of privacy by retaining raw sensor data on-device and transmitting only p
arXiv:2609.28716v1 Announce Type: cross Abstract: This paper investigates temporal neural networks for mbox{end-effector} position mbox{estimation} of an aerial continuum manipulator (ACM) operating u
arXiv:2609.28739v1 Announce Type: new Abstract: Automatic speech recognition models are audited for demographic fairness at full precision, yet the models that ship to production have been quantized,
Tesla is shifting its focus from electric cars to producing the Optimus Gen‑3 humanoid robot, targeting 1,000 units per week by the end of 2026. Engineers report major difficulties with complex roboti
Compute (EC2) opened the front door to the first generation cloud. Agents need something different: compute, inference, and data working as one. We built the cloud that delivers all three as one simpl
arXiv:2609.30210v1 Announce Type: new Abstract: Layer-wise visual-text similarity in Multimodal Large Language Models (MLLMs) is widely interpreted as evidence that the language model progressively in
💯💯”The current agentic framework is fully unsafe and must be redesigned from scratch based on different fundamental principles.” Some observations around the interview Q:Can be AI test environments be
arXiv:2609.28479v1 Announce Type: cross Abstract: Conversational AI increasingly mediates intimate-partner communication, and refusal logic at the inference layer now functions as a governance thresho
arXiv:2609.29187v1 Announce Type: new Abstract: One of the most important problems in medicine is to facilitate prediction. In this study, we propose entropy triangle method, a novel framework for pre
The era of omni agents is upon us. This is a great report by the Qwen Team on their omni-modal agents. They present Qwen3.8-Omni-Flash, a natively multimodal model trained for long-horizon agent tasks
arXiv:2609.28653v1 Announce Type: cross Abstract: Retrieval-augmented question answering requires control decisions about when to decompose a question, search, reformulate, extract evidence, synthesiz
arXiv:2609.29730v1 Announce Type: new Abstract: Bias in AI systems is typically framed as a flaw to be minimized, yet it also serves as a critical indicator of underlying weaknesses in data, modeling
arXiv:2609.29530v1 Announce Type: new Abstract: Validating a model on a time series asks for three things at once: each training run should use most of the sample (sufficiency), the test sets should t
arXiv:2506.20584v3 Announce Type: replace Abstract: The most popular graph indices for vector search use principles from computational geometry to build the graph. Hence, their formal graph navigabili
arXiv:2609.29345v1 Announce Type: new Abstract: Enterprise governance requires decisions, evidence, and accountable authority; it does not require every review task to retain its current human impleme
arXiv:2609.28782v1 Announce Type: new Abstract: In scientific machine learning, Delta-learning trains models on residual errors relative to physical baselines, assuming that more accurate baselines wi
The US government wants to spend $30.3 million over the next five years on an improved form of lie detector, according to a Department of Defense budget request. The program, called Polygraph+ or Poly
arXiv:2609.29674v1 Announce Type: cross Abstract: Sequential task updates are fundamental to continual learning, but their recency bias can impose a lasting performance cost. We study this cost in an
arXiv:2609.29045v1 Announce Type: cross Abstract: Open-weight LLMs give downstream users control over the inference stack, but this flexibility can undermine post-release guarantees that sensitive kno
There is an extensive and ongoing review related to our agents’ use of internet access during training and evaluation. We’ve been publishing summaries at the link below and will continue to. We have n
arXiv:2609.28682v1 Announce Type: new Abstract: Post-training hybrid reasoning models in NoThink mode has attracted growing interest as a way to improve performance while keeping inference fast. Howev
arXiv:2609.29709v1 Announce Type: cross Abstract: An LLM judge scores a bank of responses against a rubric, and the reliability comes back at 0.52. What has been measured? Judge evaluation has begun b
arXiv:2602.05145v2 Announce Type: replace-cross Abstract: Speculative decoding can substantially accelerate LLM inference, but realizing its benefits in practice is challenging due to evolving workloa
arXiv:2609.28576v1 Announce Type: new Abstract: Historical observations are not always fixed: statistical agencies revise previously published values as new evidence arrives. Forecasting from a contem
arXiv:2501.18963v4 Announce Type: replace-cross Abstract: Time-Varying Bayesian Optimization (TVBO) is the go-to framework for optimizing a time-varying, expensive, noisy black-box function f. However