Knowledge catalogue
This is the Qwen3.8-27B setup I actually use every day on one RTX 5090. I wanted to write it down with enough detail that another 5090 owner can reproduce it instead of guessing which memory knobs I u
arXiv:2608.19380v1 Announce Type: new Abstract: While modern autonomous driving systems excel at perception tasks such as object detection and trajectory prediction, they lack the high-level causal re
arXiv:2608.19646v1 Announce Type: new Abstract: Visual understanding in sports has emerged as a hot topic in computer vision in recent years. Most existing basketball video datasets adopt single actio
arXiv:2512.10668v2 Announce Type: replace Abstract: A deep understanding of the physical world is essential for robotic manipulation and physically realistic simulation. While current methods, includi
arXiv:2608.18734v1 Announce Type: new Abstract: 4D understanding and reasoning is a fundamental capability for embodied AI agents operating in dynamic physical environments. However, existing vision e
arXiv:2608.19140v1 Announce Type: new Abstract: Frontier language models are compared, marketed, and benchmarked on capability -- what their best or average output can achieve. I argue this measures t
arXiv:2608.17882v1 Announce Type: new Abstract: Trajectory prediction is central to safety in autonomous driving, yet learning-based predictors tend to degrade sharply when encountering scenarios poor
arXiv:2608.17933v1 Announce Type: new Abstract: Financial time series exhibit non-stationary and heterogeneous statistical properties, making change-point detection challenging because no single unsup
arXiv:2509.12040v3 Announce Type: replace-cross Abstract: Open-Vocabulary Remote Sensing Image Segmentation (OVRSIS), an emerging task that adapts Open-Vocabulary Segmentation (OVS) to the remote sens
Grok 4.6 is #1 on healthcare questions Grok 4.6 just took the #1 spot on MedAgentBench....one of the most interesting benchmarks for real-world agentic healthcare tasks and Grok now has two generation
Howdy, I'm back again - running my favorite benchmark (it's still unsaturated for the time being so might as well!) previous runs a b https://github.com/michaelasper/benchmarks/blob/main/qwen3.8-27b-p
arXiv:2604.02118v2 Announce Type: replace Abstract: Natural language explanations of time series data are increasingly produced by foundation models in high stakes domains, making factual correctness
arXiv:2608.15932v1 Announce Type: new Abstract: As state-of-the-art machine translation models saturate standard benchmarks, the field needs more challenging evaluations to distinguish between models
arXiv:2608.16614v1 Announce Type: new Abstract: Geospatial Foundation Models (GeoFMs) are most commonly ranked and selected by accuracy on standard benchmark conditions via averaged ranks. We show tha
arXiv:2608.14903v1 Announce Type: new Abstract: Quantitative forecasts of frontier artificial intelligence often connect dated targets to trends in benchmark scores, training compute, release time, or
arXiv:2608.14615v1 Announce Type: new Abstract: Large Language Models (LLMs) perform well on established code-generation and mathematical-reasoning benchmarks, but their capabilities in mechanics and
arXiv:2608.15095v1 Announce Type: new Abstract: AI systems deployed outside clean benchmark settings often rely on observations that are incomplete, unstable, costly, or degraded by monitoring failure
arXiv:2608.14391v1 Announce Type: cross Abstract: Recent video generators can fabricate realistic depictions of wars, disasters, public emergencies, and other real-world crises, creating substantial r
arXiv:2608.13580v1 Announce Type: cross Abstract: Jais 2 is a family of Arabic-centric large language models developed jointly by MBZUAI, Cerebras, and Inception, designed to advance Arabic-centric la
arXiv:2608.14221v1 Announce Type: new Abstract: Autoformalization is commonly framed as translating natural-language mathematical statements into machine-verifiable formal languages such as Lean 4. Ho
arXiv:2608.14379v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have recently achieved promising performance in robotic manipulation. However, existing benchmarks mainly evaluate
arXiv:2608.13756v1 Announce Type: new Abstract: Two GPU kernels implementing the same scaled INT8 GEMM interface are usually treated as interchangeable. We test that assumption: holding the checkpoint
This is a HANDWRITTEN post. I spent way too much time trying to get fast inference on Apple Silicon. This post is for people who want to know what's the latest on running local models on their mac, an
arXiv:2608.12593v1 Announce Type: new Abstract: Discovery---formulating novel generalizations---is a central part of the scientific process. Despite its importance, there is a gap in the current AI be
arXiv:2608.12904v1 Announce Type: new Abstract: Clinical intelligence requires estimating a patient's underlying condition from incomplete observations rather than learning isolated mappings from scan
arXiv:2512.19799v2 Announce Type: replace Abstract: Advances in LLM reasoning and tool use have enabled agentic science, yet frontier theoretical and computational physics remains challenging because
arXiv:2608.13239v1 Announce Type: new Abstract: Training Multimodal Large Language Models for audio-visual social understanding is a crucial step toward embodied social intelligence. Chain-of-thought
arXiv:2608.13495v1 Announce Type: new Abstract: Efficiently retrieving relevant clips from large-scale driving logs is essential for data curation, model development, and safety analysis. Structured a
arXiv:2608.13168v1 Announce Type: new Abstract: As large language models (LLMs) are increasingly applied for emotional companionship, evaluating their behavior and capabilities in intimate relationshi
arXiv:2608.11444v1 Announce Type: cross Abstract: Drug response prediction (DRP) models are an active area of research in pharmacogenomics, with growing potential to accelerate the identification of e
arXiv:2608.10430v1 Announce Type: cross Abstract: Large Language Models (LLMs) deployed as AI agents frequently exhibit user specification-grounding failures, executing hallucinated, undesired actions
arXiv:2608.10886v1 Announce Type: new Abstract: Robots operating in human environments need memories that capture not only what objects exist and where, but also how people use them over time and how
arXiv:2608.11002v1 Announce Type: cross Abstract: Text-to-image (T2I) generation has achieved remarkable progress in recent years. However, existing research has largely focused on English-only settin
arXiv:2608.10692v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as mobile assistants, where a key challenge is leveraging personal information scattered across
arXiv:2608.10932v1 Announce Type: cross Abstract: Understanding camera motion is fundamental to video perception, with applications in spatial intelligence and controllable video generation. Multimoda
arXiv:2608.07775v1 Announce Type: new Abstract: Mobile agents have achieved promising results on clean online benchmarks such as AndroidWorld, yet their performance often degrades sharply in real-worl
arXiv:2608.08634v1 Announce Type: new Abstract: Open-weight language models from Chinese AI labs caught up on benchmarks relative to proprietary frontier models in recent months. Yet their reliability
arXiv:2608.07796v1 Announce Type: new Abstract: Large language models perform strongly on medical knowledge benchmarks, but reliable clinical deployment requires agents to conduct defensible investiga
arXiv:2608.09443v1 Announce Type: new Abstract: Large language model (LLM) agents can support medication review between clinical visits, but safe choices for older adults with multimorbidity depend on
Been benchmarking DSv4 Flash 0731 on a Flow Z13 (Ryzen AI MAX+ 395, Radeon 8060S / gfx1151, 128GB LPDDR5X) for the past week. Figured I'd share what actually works and what doesn't — there are a lot o
arXiv:2608.09692v1 Announce Type: cross Abstract: Many of the series that generative time-series models are benchmarked on place a large probability mass on a single value --- it does not rain, no rid
arXiv:2511.18121v2 Announce Type: replace-cross Abstract: While Multimodal Large Language Models (MLLMs) excel on benchmarks, their processing paradigm differs from the human ability to integrate visu
arXiv:2603.15506v2 Announce Type: replace-cross Abstract: We argue that the current practice of evaluating AI/ML time-series forecasting models, predominantly on benchmarks characterized by strong, pe
arXiv:2608.06712v1 Announce Type: new Abstract: Model robustness against natural image corruptions is essential for safety-critical applications. While existing methods primarily focus on implicit rep
table bench https://huggingface.co/bartowski/endless-frontier_BigBang-v1-GGUF I'm downloading this model only because Bartowski converted it to .gguf, so it might be interesting. Doubts : The headline
The future of FDE work seems closely related with all work around evals/posttraining/RL envs. FDEs are effectively responsible for the following: 1. Define the business problem. 2. Codify the business
arXiv:2608.05747v1 Announce Type: new Abstract: Spatial intelligence is fundamental to embodied agents, yet existing benchmarks focus on local spatial perception from single or few viewpoints, overloo
arXiv:2608.05485v1 Announce Type: new Abstract: Evaluating generated videos remains challenging because existing benchmarks rely on fixed evaluation content, cover only a subset of generation and edit
The Amazon SageMaker Python SDK v3 now exposes generative AI inference recommendations in Amazon SageMaker AI directly in your notebook. Benchmark an endpoint, generate data-driven deployment recommen
arXiv:2608.04424v1 Announce Type: new Abstract: Existing document understanding benchmarks have largely focused on locating page elements, yet real-world document intelligence requires models to reaso
arXiv:2608.04726v1 Announce Type: new Abstract: Multimodal large language models increasingly reason over screenshots and documents where the task itself may be written in pixels. Yet benchmarks usual
daily reminder not to trust benchmarks and run it yourself. claimed e2e speedup is ~40%, forwards are ~140% faster I would wager that compared to a naive kernel anyone can write it's more in the range
arXiv:2601.17003v2 Announce Type: replace-cross Abstract: Mental-health AI safety is typically evaluated with small, simulation-based benchmarks that may not reflect the linguistic and contextual dive
arXiv:2607.11844v2 Announce Type: replace Abstract: Recent Multimodal Large Language Models (MLLMs) achieve strong performance on single-view video understanding benchmarks. However, sports videos inv
Harness choice is a big deal. So much room to advance and improve results across the board with agent harnesses. Great paper highlighting this. New research releases DataSpace, a benchmark where data
arXiv:2608.02620v1 Announce Type: new Abstract: LLM-as-a-judge evaluation has become a dominant paradigm for ranking language models, yet the ecosystem remains fragmented: most benchmarks ship their o
arXiv:2606.15974v2 Announce Type: replace Abstract: Despite the significant advancement of LLMs in conversation summarization, their evaluation remains limited by insufficient scenarios, input lengths
arXiv:2608.00004v1 Announce Type: new Abstract: Grading natural-language mathematical proofs is a recurring cost in evaluating math-reasoning systems, and frontier LLM judges are expensive. We ask whe
arXiv:2608.02112v1 Announce Type: new Abstract: Embedding benchmarks measure standalone model quality, but they do not establish whether a low-cost retriever contributes complementary ranking informat
arXiv:2602.01132v2 Announce Type: replace Abstract: Tasks such as solving arithmetic equations, evaluating truth tables, and completing syllogisms are handled well by large language models (LLMs) in t