Knowledge catalogue
arXiv:2609.15680v1 Announce Type: new Abstract: Quadrotor navigation in cluttered 3-D environments requires global guidance while local motion remains subject to collision and motion limits. Harmonic
Two months ago I announced I had found a new dynamic quant method called Voodoo Quant which was SOTA for the most aggressive quant levels on some smaller Qwen3.5 GGUF models. I kept the methodology pr
arXiv:2609.15939v1 Announce Type: cross Abstract: Language-model agents increasingly operate over complete software repositories, yet cybersecurity evaluations primarily measure whether they can detec
arXiv:2506.24092v3 Announce Type: replace Abstract: Adapting large pretrained vision models to medical image classification is often limited by memory, computation, and task-specific specializations.
arXiv:2609.14706v1 Announce Type: cross Abstract: How should a Kronecker-factored Hessian approximation be chosen for post-training quantization? We address this question through WaterKron, which comb
arXiv:2609.14733v1 Announce Type: new Abstract: Hybrid Deep Learning for equity index forecasting is limited by three problems: propagation of OHLCV noise into derived technical indicators (TIs), chan
arXiv:2504.06532v2 Announce Type: replace-cross Abstract: Wind direction forecasting plays a crucial role in optimizing wind energy production, but faces significant challenges due to the circular nat
arXiv:2609.15150v1 Announce Type: new Abstract: Unpaired cross-modal distillation transfers grade structure from histopathology into a micro-ultrasound (micro-US) encoder by aligning a pooled needle-r
Well.. @levie and I filmed this episode of Training Data a week or two ago, when the “current thing” was Doug Leone’s novacaine root canals instead of pacing the frontier… Simpler times! But Aaron’s a
arXiv:2609.15579v1 Announce Type: new Abstract: An airborne sensor on a contested link cannot send video, so the appealing move is to send findings instead and report the ratio between the two. We eva
Personally, I think the whole 'AI (LLMs) is going to take over' is just BS marketing. They've been pushing this doom-and-gloom since 2019, and we all know the models back then were nowhere near as cap
arXiv:2609.15064v1 Announce Type: new Abstract: Reinforcement learning (RL) is widely utilized in large language model training to improve targeted capabilities, yet how RL reshapes a model remains po
arXiv:2609.13232v1 Announce Type: new Abstract: A robot pruning trees needs two facts per pixel: whether it belongs to a tree, and its distance. Both are usually obtained via task heads attached to a
arXiv:2609.14247v1 Announce Type: new Abstract: Bird-strike mitigation at wind farms requires identifying distant birds that span only tens of pixels, so the classifier's input resolution N is a desig
arXiv:2609.15191v1 Announce Type: new Abstract: Since late 2022, a Limitations section has become mandatory at many top-tier NLP conferences. The growing number of accepted papers at these venues has
arXiv:2609.14899v1 Announce Type: new Abstract: Neural 3D scene editing is often evaluated by semantic alignment alone, although a convincing result may alter unrelated content or become inconsistent
arXiv:2609.13984v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models combine a pretrained vision encoder, a language backbone, and an action head, but their relative contribution has
arXiv:2603.18136v2 Announce Type: replace-cross Abstract: Continuous-variable systems enable key quantum technologies in computation, communication, and sensing. Bosonic Gaussian states emerge natural
arXiv:2609.15309v1 Announce Type: new Abstract: Large language model (LLM) agents allocate test-time compute adaptively as they revise solutions, use tools, explore alternatives, and decide when to st
arXiv:2609.13148v1 Announce Type: cross Abstract: Large language models are increasingly deployed as synthetic consumer panels, promising 97% cost reductions over traditional surveys. Yet aggregate va
arXiv:2609.13642v1 Announce Type: new Abstract: We argue that a recurring failure in the evaluation of deployed AI systems occurs when data collected for operational monitoring or regulatory complianc
arXiv:2609.13824v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to evaluate the responses of other language models. This approach, known as LLM-as-a-Judge, is faster
arXiv:2609.15305v1 Announce Type: cross Abstract: Urban region representation learning commonly combines heterogeneous data sources, such as mobility flows, points of interest, and land-use informatio
arXiv:2609.13777v1 Announce Type: cross Abstract: Learned components are increasingly integrated into geometric visual--inertial estimators to provide motion, depth, bias, uncertainty, or confidence c
arXiv:2609.14500v1 Announce Type: new Abstract: AI scaling studies increasingly evaluate systems that combine a pretrained model with retrieval, search, verification, tools, and interaction. Yet a hig
arXiv:2609.13709v1 Announce Type: new Abstract: Human corrections identify editable spans, but the examples receiving corrections may come from a selective feedback channel. We analyze this interactio
arXiv:2609.14146v1 Announce Type: cross Abstract: Vision-language-action (VLA) deployment can reduce inference latency while changing closed-loop task behavior. We evaluate HuggingFaceVLA/smolvla_libe
arXiv:2609.13564v1 Announce Type: new Abstract: We study KL-regularized contextual bandits under both reward and preference feedback. We show that greedy sampling can achieve logarithmic regret withou
arXiv:2609.13889v1 Announce Type: cross Abstract: Harness design has transformed the development of LLM-based agents by integrating memory, tool use, and runtime control. However, this design also int
arXiv:2609.15801v1 Announce Type: new Abstract: We introduce loss-conditioned state execution, a model-agnostic method that decides whether to execute a world model's fixed feasible proposal or retain
arXiv:2609.15781v1 Announce Type: cross Abstract: Pretrained world models, learned simulators that encode an observation into a latent state and predict how it evolves under actions, are beginning to
arXiv:2609.15106v1 Announce Type: new Abstract: Large language models can hallucinate even when the knowledge required for a correct answer is already available. We study this failure through a latent
arXiv:2609.15397v1 Announce Type: new Abstract: AI agents increasingly execute long-running workflows that externalize effects through independently supplied tools. Under retries, speculative executio
arXiv:2609.14157v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed with external tools that extend what they can do beyond their own knowledge. Tools help on tasks
I reallise this is not exactly a locally hostable model, at least definitly not on my hardware. But I figured some of you might have some insight on this. I run an agentic coding benchmark. The model
arXiv:2609.07474v2 Announce Type: replace Abstract: Language models compute over tokens: language is their input, their output, and increasingly their internal representation. Whether language should
arXiv:2609.15620v1 Announce Type: new Abstract: Adaptive meshes enable neural operators for partial differential equations (PDEs) to allocate spatial samples and computation according to local physica
arXiv:2609.07093v2 Announce Type: replace Abstract: Retrieval-augmented generation (RAG) enables large language models (LLMs) to answer questions by accessing external knowledge and has been widely ad
Which AI models are most likely to cheat when given the chance? To find out, we built CheatBench [https://cheatbench.ai] : a benchmark that tests whether agents attempt to cheat when given difficult t
arXiv:2504.07825v2 Announce Type: replace Abstract: Commonsense reasoning is a key language model capability, as it is purportedly a prerequisite for many basic tasks, unlike specific factual knowledg
arXiv:2609.15404v1 Announce Type: new Abstract: Multi-teacher on-policy distillation (OPD) is becoming the standard way to integrate specialist capabilities into one model: train experts with RL, then
arXiv:2609.15293v1 Announce Type: new Abstract: When Emergence World placed frontier LLM agents in an unsupervised multi-agent simulation, the results were alarming: agents committed crimes, starved,
Why oh why should we trust the companies to do so, @DavidSacks? I missed the part where they have earned our trust. Top AI companies Anthropic and OpenAI should make products and pace their own progre
Wild! Every Democrat should read this and think hard about how this could be. Americans are concerned about AI, hate data centers, and hate Trump, who has loudly embraced the industry over and over ag
In a September 2026 poll titled “Will Anthropic and OpenAI succeed in meaningfully slowing frontier AI progress…”, participants were asked whether these companies could significantly slow development
arXiv:2609.13676v1 Announce Type: new Abstract: Markov decision processes (MDPs) are used to support decision-making in conservation of biodiversity, but policies, even over small state spaces, can be
arXiv:2606.12852v2 Announce Type: replace Abstract: Rapid advances have been made in developing general-purpose embodied agent in environments like Minecraft through the adoption of LLM-augmented hier
arXiv:2609.15870v1 Announce Type: new Abstract: Scaling generalist policy models with heterogeneous data is limited by the lack of unified, low-noise action supervision. Human egocentric videos are ab
arXiv:2609.15130v1 Announce Type: cross Abstract: woma is a real-time foundation model for gastrointestinal endoscopy: a network trained without labels on about a million endoscopy frames, from which
arXiv:2609.15213v1 Announce Type: new Abstract: Scaling humanoid whole-body control toward general-purpose deployment requires large human motion corpora and training experience shared across robot bo
arXiv:2609.13647v1 Announce Type: new Abstract: The rapid development of unmanned aerial vehicle (UAV) technology has made aerial-image object detection increasingly important for natural-resource mon
You are what you eat and AI models especially so https://x.com/EMostaque/status/2099580512675262512?s=20 The Labs need to focus on 10x or 100x their effort on ALIGNMENT. Stop training the models on th
arXiv:2609.14184v1 Announce Type: new Abstract: Neural Architecture Search (NAS) automates network design, but evaluating a single candidate requires training it to convergence, making exhaustive sear
arXiv:2603.18614v2 Announce Type: replace Abstract: Tool-augmented large language models (LLMs) must tightly couple multi-step reasoning with external actions, yet existing benchmarks often confound t
arXiv:2609.13969v1 Announce Type: new Abstract: Ptychographic phase reconstruction is commonly formulated as an iterative inverse problem, requiring repeated object-probe updates and resulting in subs
arXiv:2609.14790v1 Announce Type: new Abstract: Detecting video highlights, the most informative or engaging moments in a video, is important for applications such as video summarization and content r
arXiv:2609.15048v1 Announce Type: cross Abstract: Let Y_s=sqrt{s}X+Z, where Z is standard Gaussian and independent of the real random variable X. We prove that, under the square-exponential moment con
arXiv:2609.13356v1 Announce Type: new Abstract: In this work, we present ZGCM-1, a fully open 7B dense foundation model trained from scratch with extreme data, system, and algorithmic efficiency. ZGCM
arXiv:2410.24205v2 Announce Type: replace-cross Abstract: Path planning in complex environments poses significant challenges, particularly in achieving time efficiency while maintaining a fair success
Tom Giles / Bloomberg: Zuckerberg says “Meta delayed shipping Muse for several months to focus on safety and security” and didn't call on other AI labs to do the same before acting — Meta Platforms In