Knowledge catalogue
arXiv:2609.34047v1 Announce Type: new Abstract: Multimodal models increasingly interpret visual environments, but their ability to recognize the same building across photographs, floor plans, elevatio
arXiv:2609.31692v1 Announce Type: new Abstract: Explainable Artificial Intelligence (XAI) has become essential in medical image analysis to ensure transparency of deep learning (DL)-based diagnostic s
Harness distillation can train general scaffolding into a model. The harness that remains is the part tied to your tools, data, users, and environment. The post Are agent harnesses dying? What harness
arXiv:2609.32550v1 Announce Type: cross Abstract: Understanding the safety risks of vision-language-action (VLA) models is essential for their deployment in the physical world. Existing safety researc
arXiv:2605.06643v2 Announce Type: replace Abstract: Despite the growing popularity of Multimodal Domain Generalization (MMDG) for enhancing model robustness, it remains unclear whether reported perfor
arXiv:2609.32240v1 Announce Type: new Abstract: A gradient descent method is arithmetically simple if the operations are limited to +,-, imes, and division x/2^t with integer t. An arthmetically simpl
arXiv:2609.34484v1 Announce Type: cross Abstract: Progress reward modeling is the problem of estimating how a robot's behavior changes task progress over time. Reliable estimation requires distinguish
arXiv:2609.33931v1 Announce Type: cross Abstract: Modern methods reconstruct or generate simulation-ready articulated objects, predicting not only their geometry but also how their parts are connected
arXiv:2607.09948v2 Announce Type: replace-cross Abstract: Cardiac amyloidosis (CA) is increasingly recognized but remains substantially underdiagnosed because its clinical and imaging phenotype overla
arXiv:2609.31930v1 Announce Type: cross Abstract: The Tangent Galvanometer (TG) is a standard undergraduate laboratory experiment for estimating the horizontal component of Earth's magnetic field (BH)
As least year's DevDay, this is what OpenAI said agents would look like. This is before OpenClaw & self-organizing swarms, so this entire approach was scraped soon after: 1) AI is evolving quite quick
arXiv:2609.32576v1 Announce Type: new Abstract: A common approach for shared autonomy blends human inputs with autonomous assistance based on the human's likely goal. However, most existing approaches
arXiv:2609.33993v1 Announce Type: new Abstract: Dynamic topology reconfiguration is central to the reliability and efficiency of large satellite constellations, yet many existing approaches rely on id
arXiv:2609.34860v1 Announce Type: new Abstract: Learning-based multi-agent communication under limited bandwidth does not only require deciding what to communicate, but also structuring messages so th
arXiv:2609.35620v1 Announce Type: new Abstract: Graph Transformers produce, for each attention head, a dense nimes n matrix of learned pairwise interactions. We ask a fundamental question: do these at
arXiv:2509.25570v2 Announce Type: replace Abstract: Vision Graph Neural Networks (ViGs) have demonstrated promising performance in image recognition tasks against Convolutional Neural Networks (CNNs)
arXiv:2609.32567v1 Announce Type: new Abstract: LAOD and similar zero-training LLM+open-vocabulary-detector (OVOD) pipelines score two things separately: class-agnostic localization accuracy (CAAP) an
arXiv:2609.32380v1 Announce Type: new Abstract: Data attribution methods used in practice (TRAK, LoGRA, EK-FAC) are post-hoc: after training they make a second pass over the training set to recompute
arXiv:2507.02915v2 Announce Type: replace-cross Abstract: Building on the Joint-Embedding Predictive Architecture (JEPA) paradigm, a recent self-supervised learning framework that predicts latent repr
arXiv:2609.33662v1 Announce Type: cross Abstract: Imperfect verifiers can assign a harmful update direction even when clipping and regularization bound its magnitude. We introduce Audit-First VAPO, wh
arXiv:2609.34924v1 Announce Type: new Abstract: An auditor who checks whether a system's weights are frozen is checking the wrong thing. Our stationarity dichotomy says that iterative self-modificatio
arXiv:2510.10902v3 Announce Type: replace Abstract: Auditing information disclosure across every datapoint during the training of LLMs is challenging. We propose a principled, attack-agnostic approach
arXiv:2609.31896v1 Announce Type: new Abstract: Robots on construction sites must detect workers who are kneeling or bending, which we call low poses. These workers can be lost from training datasets
arXiv:2609.33891v1 Announce Type: new Abstract: Multicalibration requires a predictor's residuals to be unbiased not only globally, but also after conditioning on the predictor's own level sets and re
arXiv:2609.33818v1 Announce Type: new Abstract: Visual anomaly detectors identify deviations from known-normal data, but their anomaly signals may mix evidence of actual anomalies with benign visual v
arXiv:2506.02914v3 Announce Type: replace Abstract: The contemporary paradigm of scaling data annotation, crucial for developing machine learning solutions, is to hire ordinary human annotators and in
arXiv:2609.33392v1 Announce Type: new Abstract: Hypergraph neural networks have achieved significant success in recent years. However, manual architecture crafting is labor-intensive and often fails t
arXiv:2601.08701v2 Announce Type: replace-cross Abstract: Accurate and generalisable segmentation of stroke lesions from magnetic resonance imaging (MRI) is essential for advancing clinical research,
arXiv:2609.35420v1 Announce Type: new Abstract: Wildlife conservation involves protecting, preserving, and managing wildlife species and their habitats. With today's rapid pace of human development, c
arXiv:2609.33802v1 Announce Type: cross Abstract: Understanding quantum phases of matter has long relied on physicists' intuition and mathematical tools such as symmetry and topology. Remarkably succe
arXiv:2609.31683v1 Announce Type: new Abstract: This work presents an end-to-end demonstration of autonomous machine learning research conducted by an agent skill on consumer hardware. The demonstrati
arXiv:2609.35530v1 Announce Type: new Abstract: Recent image generation models can take multiple reference images as input and combine them into a new image. However, multi-reference image generation
arXiv:2506.08140v2 Announce Type: replace Abstract: Despite long-standing efforts in accelerating scientific discovery with AI, building AI co-scientists remains challenging due to limited high-qualit
arXiv:2609.31848v1 Announce Type: new Abstract: The Gromov-Wasserstein (GW) distance measures the discrepancy between metric measure (mm) spaces and identifies optimal alignments between them based so
arXiv:2609.31813v1 Announce Type: cross Abstract: Dormant Awakening (DA) specializes a magnetic resonance imaging (MRI) reconstruction model by fitting a small set of zero weights to one labeled slice
ci : update the oneAPI toolkit to 2026.1 (#29273) ci : update the oneAPI toolkit to 2026.1 oneDNN is removed from Intel Deep Learning Essentials in 2026.0, so staying on the deep-learning-essentials p
common : use fs::path for cache dirs (#29595) Avoid useless string conversions on Windows. No need for BSD or emscripten special cases. Signed-off-by: Adrien Gallouët angt@huggingface.co Website: http
chat : fix Muse Glimmer ignoring response_format json_schema with --jinja (#29615) chat : fix Muse Glimmer ignoring response_format json_schema with --jinja Fixes #29613 chat : accept json fences and
vulkan : reuse descriptor sets when bindings are constant (#29280) vulkan : reuse descriptor sets when bindings are constant vulkan : bump buffer_destroy_count before destroying the buffer Website: ht
llama : fix init in several tools/examples (#29632) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/51066139 macOS/iOS: macOS Apple Silicon (arm64) macOS Ap
ggml : collect all input tensors into graph_inputs (#29634) graph_inputs was populated while splitting the graph, so it only contained the inputs that are used as srcs of some node. With pipeline para
common : add fs_write_atomic() (#29642) Check for buffered write errors when closing downloaded files. Use UTF-8 paths when writing ETag files on Windows. Write in binary mode on Windows. Signed-off-b
tests : adjust server string regex to also match m2 utlra results (#29648) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/51122498 macOS/iOS: macOS Apple S
common : use fs::path for config dir (#29649) Signed-off-by: Adrien Gallouët angt@huggingface.co Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/51176378 ma
server : remove the built-in UI's service worker when the UI is not served (#29565) With --path or --no-ui, /sw.js returned 404, and a 404 does not remove a service worker, so browsers kept showing th
common : stop accepting draft tokens at EOG (#29638) common : stop accepting draft tokens at EOG cont : remove the test Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/a
hexagon: add FP32 GELU_ERF and GEGLU_ERF support (#29631) hexagon: add FP32 GELU_ERF and GEGLU_ERF support hex-erf: reduce register pressure in kernels Website: https://llama.app Attestations: https:/
ggml : require input tensors to be GGML_OP_NONE (#29647) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/51266318 macOS/iOS: macOS Apple Silicon (arm64) mac
ggml : accumulate f16 dot products in f32 on AVX512-FP16 (#29545) Supersedes #29530 Signed-off-by: Adrien Gallouët angt@huggingface.co Website: https://llama.app Attestations: https://github.com/ggml-
vocab : keep NORMAL in PLaMo-2 and PLaMo-3 (#29580) vocab : keep NORMAL in PLaMo-2 and PLaMo-3 The PLaMo-2 and PLaMo-3 vocabularies mark as NORMAL. Current EOG token heuristic matched it by text and a
ggml : fix c++ odr by properly using GGML_COMMON_DECL_CPP (#29504) fix c++ odr by properly using GGML_COMMON_DECL_CPP using actual field rather than macro Co-authored-by: Georgi Gerganov ggerganov@gma
vulkan: MOE aware mat_mul_id tile selection (#29182) mut_mul_id selected its matmul tile with total token count. For MoE dispatch grid the true N per workgroup is per-expert rows. At pp128 on Sarvam 3
vulkan : Load F32 A matrix 2 at a time when its 2-aligned (#29254) It turns out Intel doesn't particularly like loading F32s one at a time and we already have the _2aliagned load logic in mul_mat_vec,
arXiv:2609.35044v1 Announce Type: new Abstract: Preference-based alignment methods such as Direct Preference Optimization (DPO) use pairwise preferences labeled by human annotators to fine-tune langua
arXiv:2609.32477v1 Announce Type: new Abstract: We propose a self-supervised framework designed to enhance the capability of scene text detectors in identifying and recognizing text in scenarios where
arXiv:2609.34641v1 Announce Type: new Abstract: Test-time adversarial defense improves the robustness of vision-language foundation models such as CLIP without retraining. However, adversarial activat
arXiv:2609.33210v1 Announce Type: new Abstract: Repetition is closely associated with memorization in generative models, but how other training images affect the retention and copying of targets remai
arXiv:2609.33041v1 Announce Type: new Abstract: Learning-rate warmup is a standard technique in language-model training, yet its duration remains largely heuristic. Common approaches use either a fixe
arXiv:2605.05386v2 Announce Type: replace-cross Abstract: Large language models increasingly operate in interactive settings where solving a task requires multiple rounds of information exchange with
arXiv:2609.34270v1 Announce Type: new Abstract: Interactive robot planning requires robots to infer and execute human intentions from natural language instructions that are often ambiguous, incomplete