Knowledge catalogue
arXiv:2610.13703v1 Announce Type: new Abstract: The fast pace in which protocols, frameworks, and technologies are being proposed for LLM-based agents results in a complex scenario for anyone aiming t
arXiv:2610.12728v1 Announce Type: new Abstract: Parameter-efficient fine-tuning has hundreds of methods, usually compared by parameter count and benchmark score. We compare them as maps. A pretrained
Disclaimer: I work for NuMind, the company behind this plugin. TLDR: Text/image (simili-)embeddings from the LLM you already have loaded :-) I've been working on making it easier to obtain embeddings
I am an independent researcher. Due to budget constraints, I shifted my 21B MoE pre-training—which I had originally planned to run on 64 H100s—to a single NVIDIA GH200 ($2.29 per hour), and I have com
arXiv:2501.17499v1 Announce Type: cross Abstract: A variety of complex biological, natural and man-made systems exhibit non-Markovian dynamics that can be modeled through fractional order differential
arXiv:2610.13480v1 Announce Type: cross Abstract: Nonlinear model predictive control (NMPC) can be applied to large nonlinear systems with complex objectives while enforcing constraints, but the cost
arXiv:2610.13184v1 Announce Type: new Abstract: While reinforcement learning with verifiable reward (RLVR) enhances reasoning in large language models, its efficacy in long-horizon multimodal tasks re
arXiv:2610.13708v1 Announce Type: new Abstract: Long-context serving runs out of KV memory before the hardware reaches its useful throughput. HiSparse stores history in host memory and fetches only th
arXiv:2610.13361v1 Announce Type: cross Abstract: As the production of software passes into the hands of software itself, coding agents are increasingly commissioned to build agents fitted to their us
arXiv:2610.13335v1 Announce Type: new Abstract: Tool-using agents increasingly require a common substrate for building, training, evaluating, distilling, and maintaining agentic systems, yet existing
arXiv:2610.12494v1 Announce Type: new Abstract: In this article, we propose algebraic integer number formats (AINF) as a framework for highly configurable and accurate compressed computation. A key pr
arXiv:2610.13354v1 Announce Type: new Abstract: The NIST Assembly Task Board #1 remains a challenging benchmark for learning-based methods in robotic manipulation. Over short horizons, it demands prec
arXiv:2610.13627v1 Announce Type: new Abstract: Evaluating large language models (LLMs) on AMLworld's smallest test splits is costly because each of over a million targets requires a separate graph pr
arXiv:2610.13724v1 Announce Type: cross Abstract: Counterfactual inference asks how an observed outcome might have differed under different circumstances, such as whether a patient would have recovere
arXiv:2610.12571v1 Announce Type: new Abstract: Most systems trained by equilibrium propagation or coupled learning are in the same class as multi-layer perceptrons: while they may be universal functi
arXiv:2610.12496v1 Announce Type: cross Abstract: Sequence models with a fixed-size state avoid the quadratic cost of attention, but face a design choice. An input-dependent state transition gives con
arXiv:2610.13623v1 Announce Type: cross Abstract: Professional agents increasingly work through command-line interfaces and multiple tools over shared workspaces containing files, messages, and busine
arXiv:2610.13078v1 Announce Type: new Abstract: Safety-aligned large language models (LLMs) remain vulnerable to jailbreaks and can over-refuse benign requests. Understanding these failures requires d
arXiv:2610.13600v1 Announce Type: cross Abstract: Large Audio Language Models (LALMs) achieve strong performance on speech-text tasks, but standard audio encoders produce hundreds of tokens for even s
arXiv:2610.13643v1 Announce Type: new Abstract: Automating biological laboratories requires robots to perform dexterous tool interactions under realistic visual conditions while handling dynamic exper
hexagon: add IM2COL_3D (#30305) hexagon: add IM2COL_3D support Assisted-by: OpenCode hexagon: add DMA paths for IM2COL_3D Assisted-by: OpenCode hexagon: avoid scalar fp16 conversions in IM2COL Assiste
vulkan: fix buffer logging on 32-bit platforms after source split (#30326) Move the vk::Buffer stream operator to the shared header so it is visible to ggml-vulkan-debug.cpp. Website: https://llama.ap
ggml: Change default visibility of symbols to hidden (#30014) See discussion in #29997. This prevents a handful of internal symbols leaking via GGML_API. Website: https://llama.app Attestations: https
vulkan: use ternary expressions to avoid switch lowering for CM2 quant block size (#30164) vulkan: specialize quant block size for CM2 matmul vulkan: use ternary expressions to avoid switch lowering f
sycl: guard DMMV reads at row tails (#29338) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/54988744 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Sil
llama : report compute graph reallocations during inference (#30329) Add an optional ggml_backend_sched_realloc_callback that user code registers with ggml_backend_sched_set_realloc_callback to be not
metal : fix mul_mat_id with duplicate ids (#30373) metal : fix mul_mat_id limits and kernel name metal : fix mul_mat_id with duplicate ids kernel_mul_mm_id_map0 assumed at most one match per token and
tests : link each test against only the libraries it uses (#30299) Give llama_build() and llama_build_and_test() a LINK keyword (default: llama-common) so call sites can declare what a test actually n
model: support vllm decision 2 model (#30378) models: support pplx-decider vllm d2 update clarify naming rule stricter validation fix ci rm redundant filter_tensors Website: https://llama.app Attestat
model: support vllm d3 models (#30383) models: support pplx-decider vllm d2 update clarify naming rule stricter validation d3 Website: https://llama.app Attestations: https://github.com/ggml-org/llama
vulkan: pack FMA for f16 accumulation, no dot product op (#29877) vulkan: pack FMA for f16 accumulation, no dot product op vulkan: dot_product packs two rows per f16 FMA vulkan: rename dot_product to
arXiv:2512.01093v2 Announce Type: replace Abstract: Multipurpose batch processes become increasingly popular in manufacturing industries since they adapt to low-volume, high-value products and shiftin
arXiv:2610.12527v1 Announce Type: new Abstract: Distribution operators need visibility of behind-the-meter photovoltaic (PV) generation, yet most residential customers are observed only through net sm
arXiv:2610.13504v1 Announce Type: cross Abstract: Generative Recommenders increasingly use Reinforcement Learning (RL) to optimize outcomes that may appear hundreds or thousands of interactions after
arXiv:2606.19386v2 Announce Type: replace-cross Abstract: Runtime monitors for autonomous agents commonly threshold an accumulated internal state - a behavioural baseline, a drift statistic, or, in ou
arXiv:2610.12907v1 Announce Type: cross Abstract: Federated vision-language models (FedVLMs) represent one of the emerging frontiers of machine learning, aiming to integrate federated learning within
arXiv:2610.13607v1 Announce Type: new Abstract: Negative polarity items (NPIs), such as 'anymore' and 'ever', are grammatical only in select environments, predominantly in the context of negation. Bec
arXiv:2610.13382v1 Announce Type: new Abstract: Kernel Ridge Regression (KRR) is a theoretically sound algorithm for nonparametric learning, which is also often used to investigate properties of deep
Write-up: https://zhebrak.io/posts/brokenml/ Repo: https://github.com/zhebrak/brokenml I built a benchmark to determine the access level agents need to successfully fix broken ML workloads (PyTorch ov
arXiv:2610.13862v1 Announce Type: new Abstract: Deploying language-model agents onboard mobile robots requires task reasoning and responsive execution within limited compute and memory. We propose BT-
arXiv:2610.12711v1 Announce Type: new Abstract: Federated Large Language Models (FedLLMs) are promising to deliver privacy-preserving, collaborative intelligence. The decentralized training process is
arXiv:2610.13948v1 Announce Type: new Abstract: Language models increasingly support or automate information retrieval from document collections too large to index. This task is difficult when it requ
arXiv:2610.13257v1 Announce Type: cross Abstract: Cross-tokenizer on-policy distillation (OPD) requires aligning teacher and student sequences before their scores can be compared. Decoded-text alignme
arXiv:2610.13057v1 Announce Type: cross Abstract: Counterfactual text editing is the ability to revise a given text in light of a hypothetical change while preserving facts not causally affected by th
arXiv:2610.12884v1 Announce Type: new Abstract: Accurate estimation of reservoir properties from seismic data remains challenging when well-log labels are sparse but three-dimensional seismic observat
arXiv:2610.12927v1 Announce Type: new Abstract: Large language models (LLMs) excel across diverse tasks, benefiting from knowledge priors, in-context reasoning, and test-time computation. Despite thes
arXiv:2610.13804v1 Announce Type: cross Abstract: Gaussian process solvers for linear partial differential equations (PDEs) return posteriors rather than point estimates, but they condition only on eq
arXiv:2610.13570v1 Announce Type: new Abstract: Reasoning models can benefit from test-time scaling, but continued reasoning may become ineffective or harmful, a phenomenon termed overthinking. Evalua
arXiv:2603.05911v2 Announce Type: replace-cross Abstract: Medical image segmentation is undergoing a paradigm shift from conventional visual pattern matching to cognitive reasoning analysis. Although
arXiv:2610.12830v1 Announce Type: new Abstract: Reasoning post-training draws on offline demonstrations and policy-generated rollouts, yet conventional supervised fine-tuning (SFT) followed by reinfor
arXiv:2610.13304v1 Announce Type: new Abstract: DAG structures can be learned from observations by incorporating acyclicity via smooth constraints, such as DAGMA's log-determinant function. Typically,
arXiv:2610.13261v1 Announce Type: new Abstract: In this paper, we propose Data-Adaptive Mahalanobis Cross-Head Attention (DAMCHA), a simple and effective attention mechanism that generalizes Multi-Hea
arXiv:2610.12658v1 Announce Type: new Abstract: We develop a data-driven sensor-placement framework and apply it to aerosol monitoring in the United Kingdom (UK). A trained convolutional Gaussian neur
arXiv:2603.18048v3 Announce Type: replace Abstract: Recent Audio Multimodal Large Language Models (Audio MLLMs) demonstrate impressive performance on speech benchmarks, yet it remains unclear whether
With the vLLM Semantic Router team we released Decision 3.0 (d3), our new SOTA decision model family ranging from 0.6B to 27B, Apache-2.0, all reading text, images and video. How it works - Built on Q
arXiv:2610.13536v1 Announce Type: cross Abstract: When a language model is distilled from a teacher that shares its base parameters, the student can inherit behavioural traits of the teacher---includi
arXiv:2610.12815v1 Announce Type: new Abstract: RDMA can reduce communication overhead in distributed machine learning systems, but realizing these benefits in production requires more than replacing
arXiv:2602.00915v2 Announce Type: replace Abstract: As robots are deployed across diverse environments, manipulation tasks require robot hands with different morphologies to satisfy varying task requi
arXiv:2610.13432v1 Announce Type: cross Abstract: Earnings call transcription presents a realistic continual learning scenario where Automatic Speech Recognition (ASR) systems are updated with new rec
arXiv:2610.13197v1 Announce Type: cross Abstract: Reinforcement learning (RL) under partial observability typically re- lies on recurrent networks to encode temporal information, with the recurrent mo