Knowledge catalogue
arXiv:2608.20394v1 Announce Type: cross Abstract: Industry pipelines that turn speech into supervised fine-tuning (SFT) data via multi-stage refinement are increasingly adopted but, to our knowledge,
arXiv:2608.20379v1 Announce Type: new Abstract: Advances in large language models (LLMs) have fueled a wave of research into agency: the ability to reason, plan, and act. This effort has produced agen
arXiv:2608.20634v1 Announce Type: cross Abstract: Agents learn to act through interaction with environments, yet the environments used for training are often manually constructed or synthesized around
https://preview.redd.it/usib0obv1blh1.png?width=1171&format=png&auto=webp&s=fa7b6e9155fcc461a2d397f9cf75aece4c72235c https://preview.redd.it/w453mok02blh1.png?width=2613&format=png&auto=webp&s=693182d
arXiv:2608.20445v1 Announce Type: new Abstract: Kernel density estimation converts finite samples into probability densities, but its performance depends critically on bandwidth selection. Classical s
arXiv:2608.21332v1 Announce Type: new Abstract: Deep-learning models of anatomy can be numerically plausible yet anatomically impossible, and they generalize poorly when data are scarce. We introduce
arXiv:2608.21187v1 Announce Type: cross Abstract: Pairwise reciprocal matrices are fundamental to the Analytic Hierarchy Process (AHP), a decision-making model. While the Direct Least Squares (DLS) me
arXiv:2608.20711v1 Announce Type: new Abstract: High-performance ML systems increasingly rely on GPU kernels whose editable source is unavailable, generated, or too distant from final machine code to
arXiv:2608.20661v1 Announce Type: new Abstract: Enterprise adoption of large language models in finance is constrained less by fluency than by trust: in Financial Planning and Analysis (FP&A) and othe
mamba2 : Flatten in/out projections to dispatch GEMM instead of GEMV (#27513) mamba2 : flatten mamba2 in/out projections to dispatch gemm instead of gemv mamba2 : remove redundant output reshape Websi
ggml : fix ggml_clamp (#27644) ggml : fix ggml_clamp cont : update ggml-alloc Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/42576162 macOS/iOS: macOS Appl
mtmd: video: fix moov atom at the end of file (#27596) mtmd: video: fix moov at the end of file Co-authored-by: rkfg rkfg@rkfg.me fix SIGPIPE windows: handle broken pipe case Co-authored-by: rkfg rkfg
ggml : shorten virtual device naming in CUDA and Metal (#27608) ggml : shorten virtual device naming in CUDA and Metal Assisted-by: llama.cpp:DeepSeek-V4-Flash-0731 ggml-metal : build device descripti
tests : disable DOTS3NOTE arch test for WebGPU (#27654) Co-authored-by: Stanisław Szymczyk sszymczy@gmail.com Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestation
metal: per-op source split + parallel compile (#26561) metal : per-op source split + parallel compile (#24021) preliminary extract common header op source split split metallib into 8 libs && load in p
metal : per-device tuned (Q, NE) for flash-attn vec (#26570) metal : per-device tuned (Q, NE) for flash-attn vec (#25750) rebase Q-generic FA vec body from 01dc936 (#23114) add 53 f16 (Q,NE) flash-att
arXiv:2608.20349v1 Announce Type: cross Abstract: Large Language Models (LLMs) exhibit extreme sensitivity to surface-level prompt variations, in which minor lexical changes can trigger disproportiona
arXiv:2608.21147v1 Announce Type: new Abstract: The cyclic structure of physiological processes offers a natural prior for self-supervised representation learning, and the cardiac cycle provides a par
Check out these talks from last month's Nerd Meetup, this time at @posthog's office in SF. @Runloop - Coordinating shared state for multiplayer agents http://Reboot.dev - How the architecture of code
arXiv:2501.10375v3 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) models, though highly effective for various machine learning tasks, face significant deployment challenges on memory-
arXiv:2601.12614v4 Announce Type: replace-cross Abstract: Hybrid-Vlasov simulations resolve ion-kinetic effects in the solar wind-magnetosphere interaction, but even 5D (2D + 3V) configurations are co
arXiv:2608.20759v1 Announce Type: new Abstract: Single-image 3D human reconstruction often suffers from over-smoothed textures and geometric inconsistencies. While diffusion models improve generative
arXiv:2608.20664v1 Announce Type: new Abstract: DreamBench-SWE is a multi-session benchmark for software-agent memory hygiene in which later software tasks depend on non-inferable evidence from earlie
arXiv:2602.06159v3 Announce Type: replace Abstract: Driven by the emergence of Controllable Video Diffusion, existing Sim2Real methods for autonomous driving video generation typically rely on explici
arXiv:2608.20381v1 Announce Type: cross Abstract: Automating slide editing requires simultaneously satisfying modification accuracy, preservation fidelity, and robustness to deck length. Existing LLM-
arXiv:2608.20964v1 Announce Type: cross Abstract: In this research, we introduce SAraBERT, an enhanced version of AraBERT which proposes inter-sentence transformer layers for extractive summarization
arXiv:2608.21233v1 Announce Type: new Abstract: The Traveling Salesman Problem (TSP) is one of the most extensively studied NP-hard optimization problems. Genetic Algorithm (GA)-based solvers, such as
arXiv:2608.21096v1 Announce Type: new Abstract: Federated learning enables privacy-preserving collaborative training, but highly heterogeneous client data remain challenging, especially in graph feder
arXiv:2608.21156v1 Announce Type: cross Abstract: LLMs have evolved from language generators to autonomous agents capable of complex, long-horizon tasks. This evolution has produced paradigms includin
arXiv:2601.06114v2 Announce Type: replace-cross Abstract: Multivariate time-series models achieve strong predictive performance in healthcare, industry, energy, and finance, but how they combine cross
arXiv:2409.11307v2 Announce Type: replace Abstract: End-to-end autonomous driving is increasingly data-driven, yet data reuse across vehicles remains limited. Each new vehicle often requires additiona
The posted content includes a Twitter announcement by Adam Schefter stating that Deshaun Watson has been named the starting quarterback for the Cleveland Browns in Week 1 against Jacksonville. Earlier
hello everyone. I'm training PPO variants on different multi-agent tasks from the VMAS library (Independent PPO / Graph PPO and such, see HetGPPO by Bettini et al.). I noticed that for every architect
It worked pretty well, digging through and analyzing some local files. Claude code regularly stops at some point and fails to continue while DSH worked for 2 h, recognized that it could benefit from r
I think we can all agree that stepping out toward the baseline in the middle of a WNBA game, getting ejected on purpose, and immediately claiming to be a victim is insanely pathetic Full video of Enes
I’m not sure if it’s because I’ve blocked all of *his defenders* or if it’s because everyone truly fucking hates this decision but I don’t think I have ever seen the Browns fan base this united over a
arXiv:2602.06621v2 Announce Type: replace-cross Abstract: This paper introduces a rigorous framework for defining generative diffusion models in infinite dimensions via Doob's h-transform. Rather than
arXiv:2608.20383v1 Announce Type: cross Abstract: Mechanical abuse can trigger thermal runaway (TR) in lithium-ion batteries through localized heat generation before sensor signals become decisive. Th
Interesting new approach to enable memory in long-running agents. Weighted Memory Tree organizes execution into tasks, subtasks, and actions, then gives every memory a retention score that moves. Even
similar to video upscaler LLMs, what's the bleeding edge right now on something similar for audio music? the idea is you feed it in with a low bitrate MONO old soundtrack, and the LLM then recreates i
arXiv:2608.20607v1 Announce Type: cross Abstract: Panels of inexpensive LLM judges increasingly make accept-or-escalate decisions. In factuality settings, accepting a claim because several reference-f
arXiv:2608.20668v1 Announce Type: cross Abstract: In recent years, a white-box neural network called ReduNet has been proposed, which employs the maximal coding rate reduction (MCR^2) principle to tra
Release: llm-anthropic 0.27 This release of the Anthropic plugin for LLM mainly provides compatibility with the recently released anthropic v1.0.0 Python library, which switches from httpx to httpx2.
arXiv:2510.13922v2 Announce Type: replace-cross Abstract: Clinical notes contain unstructured text provided by clinicians during patient encounters. These notes are usually accompanied by a sequence o
arXiv:2608.20429v1 Announce Type: cross Abstract: We study how angular energy signals composed of non-negative Monte Carlo path samples can be compressed and reconstructed for irradiance using finite
arXiv:2608.21265v1 Announce Type: new Abstract: Large language models often rely on Chain-of-Thought (CoT) reasoning to solve complex tasks, but verbose reasoning traces introduce substantial inferenc
arXiv:2608.21330v1 Announce Type: new Abstract: Accurate prediction of off-road vehicle motion over deformable terrain remains challenging because sinkage, slip, and traction vary with local soil cond
arXiv:2608.20354v1 Announce Type: cross Abstract: This study introduces NeuroStrata, a connectivity-aware deep representation learning framework for EEG-based mental stress analysis using Time-Varying
NVIDIA’s new GPUs in the Vera Rubin and Blackwell families set a new benchmark for agentic‑AI performance per watt on AgentX, an open‑source inference test that models realistic multi‑step, tool‑using
arXiv:2608.20932v1 Announce Type: new Abstract: Layout-to-image generation enables explicit spatial control through bounding-box layouts, yet bounding boxes specify only instance locations and cannot
TL;DR: I'm planning to spend around 100 on cloud GPUs to benchmark Qwen3.8-27B with a focus on questions that actually matter when running it locally: different quant levels/providers, 8-bit vs 16-bit
arXiv:2608.21359v1 Announce Type: cross Abstract: We develop a new direct accelerated Newton method for minimizing convex functions with Lipschitz continuous Hessian. The algorithm uses only primal va
arXiv:2608.20801v1 Announce Type: cross Abstract: While Large Language Models (LLMs) have significantly advanced reranking in recommendation, effectively leveraging item-side information remains chall
arXiv:2608.20638v1 Announce Type: cross Abstract: The edge-of-stability (EoS) phenomenon of Adam has been widely observed, while its underlying dynamical mechanism is not yet fully understood. We stud
For the GPU poor among us: I'm curious what results you're getting with low quants of Qwen 27B 3.8. My main inference hardware is limited (Mac mini M4 24 GB), but I'm getting great results with Unslot
With vision enabled I am able to run at 150k context on a single RTX 3090 and the results are just amazing. I was even able to write a gmail plugin for DeepSeek harness with locally hosted Qwen 3.8 27
arXiv:2608.20389v1 Announce Type: new Abstract: A production agent harness must discover and rank, from a growing library of skills, the one most appropriate for a user's task. At small scale this sel
arXiv:2608.21023v1 Announce Type: new Abstract: Word alignment has traditionally been studied between sentences, but many cross-lingual tasks increasingly require correspondences across full documents
arXiv:2608.20341v1 Announce Type: new Abstract: Frontier coding agents backed by large language models with context windows from hundreds of thousands to millions of tokens are restructuring the Softw
arXiv:2608.21203v1 Announce Type: new Abstract: Technology change management in large financial institutions depends on risk assessments that are accurate, consistent, and auditable. In practice, many