Search: “productivity”

Really strong benchmark paper on coding agents. Claude Opus 5 running under Claude Code passes 23.9% of the evaluations. An expert human reference scores 82.2%. Here is what the task actually is. The

Replit is officially in London. 🇬🇧 As we open our first international office here today, we’re honored to mark this important milestone with @MayorofLondon, Sadiq Khan and his team, His Majesty’s Gove

arXiv:2609.04556v1 Announce Type: new Abstract: Runtime traces are becoming a central substrate for understanding agentic systems, yet interpretation has focused largely on what the agent did. Workpla

arXiv:2603.29566v2 Announce Type: replace Abstract: We study polynomial group convolutional neural networks (PGCNNs) for an arbitrary finite group G. In particular, we introduce a new mathematical fra

arXiv:2609.05190v1 Announce Type: new Abstract: In this paper we illustrate a novel architecture generating interpretable behavior and explanations. We refer to this architecture as the Mirror Agent M

TL;DR: switching KV cache to f16 may give a boost in speed if using MTP and ngrams. I have a self-built 'AI mega-cluster' with 2x P40s on a cheap Chinese motherboard and a Xeon CPU (around $1,100 to b

Hello, I'm a bit obsessed with cache management on local LLMs. For the last few days I've been working on cache management on vLLM with my 2x DGX Spark and DeepSeek v4 Flash 0731. I felt something was

Otaku is an LLM frontend, primarily designed for roleplay, an alternative to SillyTavern and the like. However, It also works for general-purpose chat with local backends (including Ollama) or cloud m

This is a weird behavior in coding models and something worth looking into. It turns that some models over-edit code that another models wrote. There is a high chance that your repo now has commits fr

arXiv:2609.03716v1 Announce Type: new Abstract: Data centers are increasingly optimized by artificial intelligence and, at the same time, increasingly loaded by it. The literature treats these as two

arXiv:2609.03502v1 Announce Type: cross Abstract: In low-resource settings, deploying TTS typically requires choosing between a large voice-cloning model with costly inference or a compact fixed-voice

arXiv:2609.03894v1 Announce Type: new Abstract: Large language models (LLMs) have become ubiquitous tools for code generation and editing. However, development teams often use multiple LLM assistants.

arXiv:2509.25175v3 Announce Type: replace-cross Abstract: Large language model (LLM) steering has emerged as a promising paradigm for controlling model behavior at inference time through targeted mani

arXiv:2609.04034v1 Announce Type: cross Abstract: While diffusion base models such as GPT-Image-2 and Nano-Banana exhibit remarkable visual expressiveness, their end-to-end generation inherently yield

Enterprise AI readiness is trailing industry rhetoric as organizations struggle to modernize infrastructure, control costs and choose appropriate applications. That gap is becoming more visible as com

arXiv:2602.08216v3 Announce Type: replace Abstract: We derive two attention operators from generalized statistical entropies. Kaniadakis entropy yields an exact full-support normalization whose weight

arXiv:2609.03801v1 Announce Type: new Abstract: We study the ordered Bernoulli-word kernel f(p,n,k)=p^k(1-p)^(n-k) and the geometry generated by its inverse-integer level sets. The binary level 2^(-n)

arXiv:2606.12821v2 Announce Type: replace Abstract: Environmental scientists spend disproportionate effort on data wrangling rather than analysis. New AI agents can be a helpful tool, but no benchmark

arXiv:2609.04105v1 Announce Type: new Abstract: Blackwell's 4-bit floating-point (FP4) tensor cores do not automatically make attention faster because softmax conversion and on-chip dependencies domin

Insightful paper from Microsoft and colleagues. If you have ever had an agent run fail 80 steps ago with no way to find where, this one is for you. (bookmark it) Agent failures show up as long complex

arXiv:2503.04997v4 Announce Type: replace Abstract: Automatic visual inspection using machine learning plays a key role in achieving zero-defect policies in industry. Research on anomaly detection is

arXiv:2609.03577v1 Announce Type: new Abstract: Language models are commonly discussed as technical artefacts, but they are obviously shaped by the linguistic worlds conveyed by data during their trai

arXiv:2609.02897v1 Announce Type: new Abstract: Speculative decoding accelerates LLM inference by drafting candidate tokens and verifying them in parallel. Tree-attention drafters such as EAGLE-3 are

arXiv:2609.04165v1 Announce Type: cross Abstract: Parameterised graph theory studies how the complexity of graph-theoretic problems depends on structural parameters of the input graph. This perspectiv

arXiv:2603.28763v2 Announce Type: replace Abstract: Acquiring labeled datasets for 3D human mesh estimation is challenging due to depth ambiguities and the inherent difficulty of annotating 3D geometr

arXiv:2609.03773v1 Announce Type: cross Abstract: Parametric computer-aided design (CAD) modeling is difficult to evaluate with a single metric. Existing CAD benchmarks often emphasize synthetic or CA

arXiv:2609.03047v1 Announce Type: cross Abstract: Libraries and archives manage large collections with limited staff and computing budgets, yet common benchmarks do not systematically test their bibli

arXiv:2603.15834v2 Announce Type: replace-cross Abstract: We introduce a spectral hierarchy of cosmic-web classifications obtained by applying simple scale-weighting kernels to the density field befor

arXiv:2609.04167v1 Announce Type: cross Abstract: Repository-level software engineering benchmarks have significantly advanced the evaluation of coding agents, but existing benchmarks primarily measur

arXiv:2609.03456v1 Announce Type: cross Abstract: Artificial intelligence (AI) is increasingly used to augment software engineering (SE) workflows. While code generation remains the main use case, org

arXiv:2609.03480v1 Announce Type: cross Abstract: We map tree species across Denmark using National Forest Inventory plots and EO data, while evaluating the potential of foundation models for large-sc

arXiv:2609.03534v1 Announce Type: cross Abstract: 3D Gaussian Splatting has become a de facto scene representation for novel view synthesis, yet robustly learning 3D Gaussian primitives from visual in

Unlike other players in the OCR space, we don't block our competitors from accessing our platform. We're also fully committed towards open, reproducible benchmarks for document parsing and extraction

arXiv:2607.17544v1 Announce Type: cross Abstract: Real-time speech-to-speech translation (S2ST) systems must balance translation quality, latency, speech naturalness, and speaker consistency. Publicly

arXiv:2609.01649v1 Announce Type: cross Abstract: With the rapid growth of live-streaming e-commerce and digital marketing, abnormal marketing behaviors have become increasingly concealed and coordina

Jennifer Pattison Tuohy / The Verge: Anker unveils the Eufy MindBase, a local AI hub for its cameras that runs an on-device, Anker-developed LLM, with a dedicated AI chip and up to 48TB of storage — T

Artificial intelligence security startup HiddenLayer Inc. today announced a 100 million Series B round, and a separate 27 million Series A went to edge security company Huskeys Security Ltd. Austin-ba

Banger paper from Google DeepMind and colleagues. (bookmark it) A model reads its entire KV cache on every generated token, even though it ends up attending to a tiny slice of it. In other words, if y

arXiv:2609.02707v1 Announce Type: new Abstract: Does the door-in-the-face technique work on language models? In humans, a large request that is refused makes a smaller follow-up request more likely to

arXiv:2609.02101v1 Announce Type: cross Abstract: Federated learning (FL) lets institutions train a shared model without exchanging data, and Low-Rank Adaptation (LoRA) makes this practical at scale b

arXiv:2609.01956v1 Announce Type: new Abstract: Kolmogorov-Arnold Networks (KANs) place learnable B-spline activations on network edges rather than fixed activations on nodes. The standard Cox-de Boor

TimesFM-3 is the third generation of Google Research's zero-shot forecasting model, and the main change from 2.5 is that it handles multivariate inputs natively instead of being limited to a single se

GPT-6 Astra is the most intelligent and aligned model in the world, and sets a new state of the art for computer use, browsing, software engineering, cybersecurity, science, and professional work. htt

Hot take on OpenAI GPT-6 Astra*, with a challenge to @gdb’s claims about it being AGI toward the end: • Looks to be pretty impressive. Multiple reports suggest it is a genuine advance. • As someone wh

arXiv:2609.01617v1 Announce Type: cross Abstract: Getting accurate, grounded answers out of large enterprise document repositories is a difficult problem. Dense vector retrieval alone frequently perfo

Krea 2 Turbo — 4-Step Distillation LoRA (work in progress) A LoRA for Krea 2 Turbo that reduces the minimum usable step count from 8 to 4. ⚡ Half the steps — 8 → 4, on Turbo's own deployment sigmas. ⏱