Knowledge catalogue
arXiv:2608.23476v1 Announce Type: new Abstract: Narrow fine-tuning on small, domain-specific datasets can produce broad and surprising changes in model behavior-a phenomenon called weird generalizatio
arXiv:2608.23001v1 Announce Type: new Abstract: Automated manuscript pipelines often regenerate an entire section to repair a local defect, allowing unrelated metrics and citations to change even when
arXiv:2608.21892v1 Announce Type: cross Abstract: The electronic circular dichroism (ECD) spectrum is a primary experimental probe for assigning the absolute configuration of chiral molecules, yet int
arXiv:2608.22378v1 Announce Type: cross Abstract: Systolic arrays (SAs) have emerged as prominent hardware accelerators for matrix operations in deep learning, while floating point number formats enab
AI agents are helping developers, teams, and businesses do more: writing and executing code, conducting research, and running dynamic workflows across systems. But that ability is often bounded by whe
arXiv:2608.21379v1 Announce Type: new Abstract: Student burnout is highly prevalent in higher education, with reported rates ranging from 12% to over 70% and consistently exceeding those of the workin
arXiv:2608.22725v1 Announce Type: new Abstract: Short-drama generation has grown into a large, industrialized pipeline, and as it scales from isolated shots to the episode level, visual continuity has
arXiv:2608.23211v1 Announce Type: cross Abstract: In this work, we study the oracle complexity of finding an epsilon-stationary point for nonconvex-strongly-convex (NC-SC) bilevel optimization using o
arXiv:2608.22223v1 Announce Type: cross Abstract: Anti-amyloid therapies and blood-based biomarkers are changing Alzheimer disease workups into a two-stage measurement workflow: screen broadly with ch
arXiv:2608.21607v1 Announce Type: new Abstract: We investigate when a sparse nonnegative matrix can be recovered from a real-valued matrix of much lower rank by zeroing out its negative elements. The
arXiv:2608.21555v1 Announce Type: cross Abstract: Modern machine learning compilers select tensor memory layouts to minimize execution cost under hardware constraints. Layout selection is global: an o
arXiv:2608.21412v1 Announce Type: new Abstract: Root cause analysis (RCA) in large datacenter networks is challenging because telemetry is noisy, partial, and asynchronous. Score-based approaches degr
arXiv:2608.22467v1 Announce Type: new Abstract: Long-horizon language-model tasks --- multi-step reasoning and tool-using agents alike --- are limited by credit assignment. We analyze it through the p
this is a practical guide (+ updated skill) on how we use real world data like traces + human feedback to make synthetic environments + evals so we can measure, harness engineer, and post-train our ag
arXiv:2511.02208v2 Announce Type: replace Abstract: Despite rapid progress, current AI agents are primarily optimized for isolated task completion. We argue for a paradigm shift toward training agents
arXiv:2608.22917v1 Announce Type: new Abstract: We present TSWAP, a deployed eight-language conversational wellness advisor grounded, via retrieval-augmented generation, in a verified knowledge base o
arXiv:2608.22116v1 Announce Type: new Abstract: The dataset provides individual vehicle speed observations on European E-roads: motorways, trunk roads, primary and secondary roads, as tagged in OpenSt
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:2608.21234v1 Announce Type: cross Abstract: These lecture notes form the first part of a master's-level course on advanced numerical linear algebra. Their aim is not only to present the classica
Metadata harmonization (standardizing labels, identifiers, and formats so datasets can work together) is still largely manual. This post shows how AI-powered metadata correction works in practice, cov
arXiv:2608.21356v1 Announce Type: cross Abstract: For sixty years, machine verification has been a major cost overhead, affordable only for exceptional artifacts. Here we report that generative AI inv
// Applying Anthropic Primitives at Large Enterprises // Frontier models collapsed the cost of writing custom code. But they did not reduce the cost of reviewing and maintaining it. Each bespoke solut
arXiv:2608.20622v1 Announce Type: new Abstract: Frontier models have collapsed the cost of writing custom code: a niche problem a specialist sees in their own domain now costs an afternoon. The cost o
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:2608.20851v1 Announce Type: cross Abstract: Agentic engineering systems have shown strong performance on general-purpose benchmarks, yet their effectiveness in enterprise resource planning (ERP)
Be sure to tune in this Wednesday! Inference Hours is back with another Kimi K3 webinar! On Wednesday, August 26, Zain Hasan sits down with Kevin Cui and Austin Silveria from Together AI's inference t
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
AI agents are the ultimate insiders. We grant them permission to read emails, query databases, and trigger API calls. They don’t just retrieve information, they take action. Agents offer incredible po
arXiv:2608.20392v1 Announce Type: cross Abstract: LLM-powered meeting assistants are deployed at scale, yet systematic evaluation of their grounding fidelity remains limited to static benchmarks that
arXiv:2310.12032v4 Announce Type: replace Abstract: The Linear Model of Co-regionalization (LMC) is a very general multitask gaussian process model for regression or classification. While its expressi
arXiv:2608.21021v1 Announce Type: cross Abstract: Real-world fault analysis in 5G and emerging 6G networks demands domain expertise to analyze free-text diagnostics, including root-cause explanations
arXiv:2608.21012v1 Announce Type: cross Abstract: Generative recommendation represents each item with a sequence of discrete Semantic IDs (SIDs) and predicts the sequence to retrieve the next item. Ty
arXiv:2608.20377v1 Announce Type: cross Abstract: Ethereum transactions admit a canonical structural form. Each execution trace is built into an abstract syntax tree of token transfers grouped by call
arXiv:2512.03262v3 Announce Type: replace-cross Abstract: Vibe coding is a new software development paradigm in which human engineers prompt a large language model (LLM) agent to complete complex codi
arXiv:2608.20840v1 Announce Type: cross Abstract: Recent advances in multimodal retrieval have improved the ability to retrieve information from visually rich documents such as PDFs and reports. Howev
arXiv:2608.20532v1 Announce Type: new Abstract: NVIDIA provides a SASS disassembler but no public SASS assembler for recent data-center GPUs, limiting controlled machine-code rewriting. We present F2A
arXiv:2512.12142v2 Announce Type: replace-cross Abstract: The Greenland ice sheet is melting at an accelerated rate due to processes that are not fully understood and hard to measure. The distribution
Nice little survey on Terminal Agents. It provides good information on what exactly is a terminal agent, and why do harness comparisons keep contradicting each other? Paper: https://arxiv.org/abs/2608
arXiv:2608.21254v1 Announce Type: new Abstract: Accurate agricultural weed detection in real-world field conditions is essential for precision agriculture, enabling targeted intervention and reducing
Our 2nd founder dinner in SF co-hosted by @jerryjliu0 and @GuangyuRobert at @Fundamental - the team behind @tryshortcutai Talking about existing moats in the AI era. Frontier labs are moving past mode
arXiv:2608.20438v1 Announce Type: cross Abstract: Population-level behavior in large-language-model (LLM) agents cannot be characterized by single-agent benchmarks. We introduce PV-SST, a peer-voted s
arXiv:2507.19290v2 Announce Type: replace-cross Abstract: We study the problem of learning a structured approximation (low-rank, sparse, banded, etc.) to an unknown matrix A given access to matrix-vec
Thanks to Unsloth Dynamic 3.0 quants coming in slightly leaner and better preserved, I settled on Qwen 3.8 27B (`UD_Q4_K_XL`) at 100K context as my daily driver for Hermes Agent and OpenCode. On an RT
arXiv:2608.20680v1 Announce Type: new Abstract: We study reinforcement learning (RL) in Continuous-Time Jump Markov Decision Processes (CTJMDPs) featuring general discrete state spaces (which need not
Bloomberg: Sources: ByteDance is merging coding platform Trae and agent-building tool Coze into Doubao, and plans to launch Doubao Work to compete with Tencent's WorkBuddy — ByteDance Ltd. is consolid
SpaceX, in partnership with Nvidia, has designed a space-optimized Vera Rubin NVL72 system for launch to orbit in Q4 next year, with significant scale in 2028 The first CPU built for agents is going t
arXiv:2608.20685v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) has no model of time: when a fact changes across a coding session - a function is renamed, an endpoint moves, a d
arXiv:2608.20918v1 Announce Type: new Abstract: Organizations maintain task-specific adapters for open-weight language models, and each new base-model release forces a migration decision: retain exist
Very interesting new paper from NVIDIA. (bookmark it) It takes a closer look at evaluating agent skills. Enterprise teams are starting to leverage shared skill libraries, and the review gate is typica
we gave Hermes a phone. it connected over MCP, picked @Uber X, and booked the ride on a real Android device, not an emulator. Claude, Codex, OpenClaw, Cursor all work the same way. Sign-in and your ag
Natasha Singer / New York Times: A look at the playbook tech giants like Google, Microsoft, and OpenAI use to shape American schools to their benefit, and the pushback against unproven AI tools — One
If you maintain an AGENTS.md or a CLAUDE.md, this one is worth your time. (bookmark it) Researchers traced 94K development events across 557 agentic coding sessions, plus 690K file-level change record
i got it last week and im really impressed. its maybe like a sonnet from last year or 6 months ago. i had built some automation for myself and a dashboard cobbled together over the years from bits of
Truman Dickerson / Business Insider: Sam Altman says AI could end up controlled by a few powerful players, partly because AI fears could push people to trade “a lot of liberty for safety” — OpenAI CEO
Hi everyone, I'm currently working on optimizing an LLM setup at my company and I'm trying to identify where the actual performance bottleneck is. Our current setup is roughly: LLM: NVIDIA Nemotron mo
Me and my team made Atomic Dynamic GGUF quants for Qwen 3.8 27B, so we wanted to see the difference between them by giving each quant the same voxel island creation task First of all we were surprised
Financial Times: Inside the World Robot Conference in Beijing, drawing over 300 exhibitors; Unitree founder Wang Xingxing said the industry's “ChatGPT moment” has yet to come — Beijing policymakers ha
Live now: our AI Architects, AI Factories Track from AI Engineer World's Fair 2026. Thesis: the model is the easy part of the factory. https://www.youtube.com/watch?v=rbjWzZK2LU0&list=PLcfpQ4tk2k0VeXE
saas isn't dead, it just has to be repurposed (+ remonetized) for agent consumption So many vendors are NOT getting this I have one or two agents I use and like. For anyone else: give me an MCP interf
We’re Hiring: Member of Technical Staff (LLM Development) 🐟 https://sakana.ai/careers/member-of-technical-staff-llm-development/#English The role: ・Develop LLMs that form the foundation of Sakana AI’s