Knowledge catalogue
arXiv:2608.02683v1 Announce Type: cross Abstract: Large Language Model (LLM) agents rely on multi-stage agentic workflows, with stages such as memory, planning, and tool execution, to accomplish compl
arXiv:2608.03228v1 Announce Type: new Abstract: Existing low rank KV cache methods preserve either model weights or key variance, neither of which directly reflects the attention scores used during in
As a market leader in enterprise agentic automation and business orchestration, UiPath is helping to pioneer an industry shift toward agentic AI. With it, the company is deploying autonomous agents to
Hey everyone! Scenema Audio is now a native ComfyUI custom node. Same model that powers scenema.ai now quantized so it fits on 8GB VRAM. When we first released it a few months ago as an API and Docker
arXiv:2608.03860v1 Announce Type: cross Abstract: We introduce SciRet, a compute-aware empirical study of retrieval-augmented generation for scientific question answering over CORD-19. Rather than pro
arXiv:2608.03327v1 Announce Type: new Abstract: Hybrid computer-use agents can act through screenshots or call text tools. We find that having a tool available does not settle which way the effect goe
arXiv:2608.03298v1 Announce Type: new Abstract: Agentic presentation generation must preserve source content, maintain coherent visual design, render specialized objects, and produce usable artifacts.
arXiv:2608.02672v1 Announce Type: cross Abstract: Cloud misconfiguration remains a leading cause of security incidents, yet whether LLMs and SLMs can generate security-compliant Infrastructure-as-Code
arXiv:2608.03842v1 Announce Type: new Abstract: When a language model fails on surface-perturbed input (typos, OCR noise, homophones), 'which layer is responsible' has three natural operationalization
arXiv:2608.03063v1 Announce Type: new Abstract: Merchant risk control at large payment platforms screens tens of millions of merchants daily, where false positives harm legitimate merchants and false
arXiv:2608.03573v1 Announce Type: new Abstract: Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) exhibit fundamentally different behaviors in enhancing multi-task reasoning for large langu
arXiv:2608.03401v1 Announce Type: cross Abstract: Large language models often reason at length before answering, increasing cost and latency. Prompts and trained settings can shorten this reasoning, b
arXiv:2509.25459v2 Announce Type: replace Abstract: Large Language Models (LLMs) show promise in generating long-form scientific explanations that synthesize evidence and connect multiple factors. How
arXiv:2608.02665v1 Announce Type: cross Abstract: A benchmark score is a measurement instrument, yet most benchmarks read each item at a single canonical surface form. We ask whether that reading is f
SITUATION DETECTED: Prime Intellect is releasing Prime Agent, a self-improving harness for coding and long-running autonomous tasks. The team reports 95.5% on ARC-AGI-3, above the human baseline, and
Skill libraries are shipping in agent harnesses on the assumption that writing skills down compounds. A new benchmark tests that directly. ContinualSkillBench covers five domains, each with 100 interc
arXiv:2608.03580v1 Announce Type: new Abstract: While Vision-Language Models (VLMs) have demonstrated remarkable performance in processing and understanding both text and images, their large parameter
arXiv:2608.04009v1 Announce Type: new Abstract: Large language models (LLMs), and the agents built on top of them, are now benchmarked heavily on whether they can finish a task -- fix a bug, drive a b
arXiv:2607.27703v2 Announce Type: replace Abstract: Vision-language models (VLMs) are increasingly used in embodied agents to interpret visual inputs, reason about spatial relationships, and make task
arXiv:2608.02668v1 Announce Type: cross Abstract: Residual connections are the de facto mechanism for training deep neural networks stably. Geodesic Normalization (GeoNorm) recasts them on a Riemannia
Hear me out before you roll your eyes. We tend to only recognize turning points in hindsight. Nobody in 1993 thought the Mosaic browser would be a history book moment, but the web is. I think Stable D
arXiv:2603.29368v2 Announce Type: replace Abstract: Driven by the advancement of 3D devices, stereo vision tasks including stereo matching and stereo conversion have emerged as a critical research fro
arXiv:2511.15339v3 Announce Type: replace-cross Abstract: Automotive telemetry data exhibits slow drifts and fast spikes, often within the same sequence, making reliable anomaly detection challenging.
arXiv:2608.02689v1 Announce Type: new Abstract: We convert 21 of 28 full-attention layers of Qwen3-0.6B-Base into KDA (Kimi Delta Attention) linear-attention layers on a single consumer-grade GPU budg
Hello, I'm the guy who made Sulphur 2. With the recent release of a certain video model, we are looking to mobilize and train Sulphur 3 on this new model. We are targeting $10,000 USD. This certain ne
arXiv:2608.03084v1 Announce Type: new Abstract: End-to-end driving requires a coherent understanding of future scenes, yet existing methods model these scenes using task-specific heads and output form
arXiv:2608.03952v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to provide conversational practice for English-as-a-second-language (ESL) learners. Effective ESL tut
arXiv:2608.03660v1 Announce Type: new Abstract: Reinforcement fine-tuning (RFT) is widely believed to inherently resist catastrophic forgetting in continual post-training of multimodal large language
arXiv:2608.03699v1 Announce Type: new Abstract: Persistent memory helps long-term agents retain knowledge, yet a single update error can repeatedly distort future retrieval and reasoning. Most existin
arXiv:2608.03319v1 Announce Type: cross Abstract: Future integrated sensing and communication (ISAC) architectures separate the sensing entity (SE) that acquires measurements from the sensing function
arXiv:2608.03557v1 Announce Type: new Abstract: Tabular-to-image methods that convert tabular data into visual representations have emerged as a novel paradigm for leveraging the high performance of d
Hello everyone Yesterday I gave a report on Gemini bugs and the techniques I learned on Gemini so far with the Engineering Prompt and interestingly today I got a very interesting and controversial ans
arXiv:2608.03263v1 Announce Type: cross Abstract: We test whether the 'compositional ignition' reported in latent-reasoning models is real computation, an instrument artifact, or inherited from verbal
arXiv:2603.20381v2 Announce Type: replace-cross Abstract: Understanding the fundamental mechanisms governing the production of meaning in the processing of natural language is critical for designing s
So I'm looking at https://huggingface.co/unsloth/DeepSeek-V4-Flash-0731-GGUF and I realize my 128GB of DRAM just isn't cutting it for this (incredibly powerful) model. If only I had another 64GB, I th
Third-party cyber evaluations involving OpenAI models And another one. I had to create a accidental-cyberattacks tag to keep track of them all! This post from OpenAI covers both the UK AI Safety Insti
arXiv:2608.03391v1 Announce Type: new Abstract: Precise anomaly localization over long-context time series is a crucial task in monitoring applications across clinical care, industrial operations, fin
arXiv:2608.02680v1 Announce Type: cross Abstract: Tool-using language-model agents repeatedly rediscover procedures they have already executed, producing traces that mix reusable structure with retrie
arXiv:2608.03916v1 Announce Type: new Abstract: Trajectory inference is a fundamental problem in many scientific domains: given a collection of unpaired snapshots of observations at discrete time poin
Try npm i -g cline on Cline!👀 Qwen3.8-Max is now available in ClinePass, a subscription for ~5x discounted access. Use it on Cline CLI w/ $4.99 special promo: npm i -g cline This is currently the most
arXiv:2608.03190v1 Announce Type: new Abstract: Neuro-oncology decisions require coordinated interpretation of serial MRI, pathology, molecular markers, treatment history, performance status, and evol
arXiv:2608.03627v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly used for automated fact-checking, yet their susceptibility to gender bias in this context remains underexp
arXiv:2608.03244v1 Announce Type: new Abstract: Image-goal visual navigation is a fundamental capability for embodied agents. Existing navigation policies efficiently predict waypoint trajectories but
arXiv:2608.03971v1 Announce Type: new Abstract: We introduce UniWorld-Design, a framework that redefines image generation from flat pixel synthesis to structured visual composition, with semantic RGBA
Today, enterprise storage must be as agile, elastic, and responsive as the workloads it supports. Filestore, Google Cloud’s first-party, secure, scalable NFS file service, can service a wide-range of
arXiv:2608.03018v1 Announce Type: new Abstract: Modern cities rely on an increasing number of digital services to operate, but residents' daily needs are still difficult to meet. Services are fragment
We run a local model instance in our company that the dev we hired built for us. We're a trade business and we want to further use our on hand hardware for it. The specs given we have is a 5090 gpu wi
Threat detection company Vectra AI Inc. today launched Vectra AI Pro, a product built to give the artificial intelligence agents now working inside security operations centers a more reliable read on
arXiv:2608.02662v1 Announce Type: cross Abstract: Reliable forecasting of nonlinear physical systems underpins scientific discovery and engineering decision-making. Yet high-fidelity simulations are p
arXiv:2608.02878v1 Announce Type: new Abstract: Large language models have shown promise for automated Verilog RTL generation, yet state-of-the-art multi-agent systems plateau at ~95% accuracy on stan
arXiv:2608.03810v1 Announce Type: cross Abstract: Large language models routinely describe socially salient targets, including political figures, countries, religions, organizations, historical events
arXiv:2505.17810v2 Announce Type: replace Abstract: Approximate nearest neighbor (ANN) search is a performance-critical component of many machine learning pipelines, and rigorous benchmarking is essen
arXiv:2608.03979v1 Announce Type: cross Abstract: We introduce Video-DeepResearch (Video-DR), extending multimodal agents from static images to continuous video streams, a setting that demands dense s
arXiv:2608.03095v1 Announce Type: new Abstract: We present VIVID (Vietnamese Idioms for Validation and Interpretation Depth), the first systematic benchmark for evaluating culturally grounded figurati
arXiv:2608.02669v1 Announce Type: cross Abstract: Docker Hub is the registry underneath most container deployments, and a flaw in a widely reused base image is inherited by every image built on it. Pr
The video is one real run, not a mock-up: grapharc go 'why did checkout latency spike at 09:14 UTC?' --model ollama/qwen3:8b A local 8B model proposes the graph → triage fanning out into four parallel
arXiv:2608.03499v1 Announce Type: new Abstract: Recent advances in persistent personal-agent frameworks are making human-centered agent networks realistic deployment targets: each user can be served b
arXiv:2608.03700v1 Announce Type: cross Abstract: Persona skills distill personal interaction histories into portable and executable artifacts for downstream agents. While enabling flexible personaliz
arXiv:2608.03994v1 Announce Type: new Abstract: We identify a previously overlooked failure mode of ALiBi positional encoding: its linear bias scaling underflows floating-point precision, which zeroes
arXiv:2602.00573v2 Announce Type: replace-cross Abstract: Class-Incremental Learning (CIL) aims to sequentially learn new classes while mitigating catastrophic forgetting of previously learned knowled