b10871
vulkan: add dedicated iq4_xs mat-vec shader (#28426) vulkan: add dedicated iq4_xs mat-vec shader Dedicated mul_mat_vec_iq4_xs for the dmmv path, replacing the generic fallback. ~+6-17% token generatio
Knowledge catalogue
vulkan: add dedicated iq4_xs mat-vec shader (#28426) vulkan: add dedicated iq4_xs mat-vec shader Dedicated mul_mat_vec_iq4_xs for the dmmv path, replacing the generic fallback. ~+6-17% token generatio
jinja: treat a null left operand of in as a plain lookup (#28620) Templates that default an optional variable to none and then test its membership in a map hit an error, while the same expression is a
mtmd: propagate video ID to bitmap (#28601) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/46201259 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Sili
model: fix granite3 moe unknown parameter count (#28632) Signed-off-by: Aaron Teo aaron.teo1@ibm.com Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/4620980
args: officially deprecate --mmap|mlock|dio (#28334) Signed-off-by: Aaron Teo aaron.teo1@ibm.com Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/46228590 ma
CUDA: replace GGML_FA_ALL_QUANTS with GGML_FA_QUANTS, more control over what is compiled (#28079) CUDA: add configurable FA quant combinations Assisted-by: Codex remove all flags but , add runtime fal
CUDA: size routed MoE MMQ N-tiles from typical expert width on RDNA3 (#28552) Recreated from #24546 Co-authored-by: Carl Philipp Klemm carl@uvos.xyz CUDA: pick MMQ tile size against ncols_opt set on t
llama : use int32_t for llama_sampler_chain_n return type (#28631) Contributes to #4574 Co-authored-by: linsen linsen@insta360.com Website: https://llama.app Attestations: https://github.com/ggml-org/
vulkan: Convert FILL to distribute workgroups in 2D to avoid exceeding maxComputeWorkGroupCount (#28592) divide workload to 2D This is to workaround FILL exceeding maxComputeWorkGroupCount for Intel G
vulkan: use spec constant for matrix matrix multiplication A-type (#25773) vulkan: use spec constant for mul mat type_a vulkan: use map for mul_mm shapes cleanup fix indentation fix cm2 and shmem init
arXiv:2609.06726v1 Announce Type: new Abstract: We present B2TFPose, a training-free zero-shot method for 6DoF pose estimation of unseen objects from RGB images. Using a single frozen DINOv3 vision tr
arXiv:2609.08725v1 Announce Type: new Abstract: In online A/B tests for real-time bidding (RTB), control and treatment models are typically trained on a shared serving log that includes data generated
arXiv:2510.09596v2 Announce Type: replace Abstract: Today's generative models thrive with large amounts of supervised data and informative reward functions characterizing the quality of the generation
Banger report from Microsoft. (bookmark it) They show that it's possible to build competitive small coding agents without traditional distillation from frontier models. This is a big deal! The work de
arXiv:2609.08029v1 Announce Type: cross Abstract: Vision Language Models have achieved strong performance on multimodal benchmarks, yet their ability to reason about culturally grounded and metaphor-r
arXiv:2609.07600v1 Announce Type: new Abstract: Tree species recognition supports forest inventory and biodiversity monitoring but still depends on scarce taxonomic expertise. Bark is visible year-rou
arXiv:2609.08055v1 Announce Type: cross Abstract: Many scientific graphs attach several variables to each node, so a single scalar edge weight cannot describe direction-dependent interactions. We mode
arXiv:2609.06922v1 Announce Type: new Abstract: Quantization makes vision language models (VLMs) cheaper to store and run by using fewer bits to represent their weights. While unchanged answers on vis
arXiv:2609.06667v1 Announce Type: new Abstract: Adaptive dosing requires policies that reduce tumor burden without excessive toxicity. Learned dosing policies are typically judged against historical o
arXiv:2609.07943v1 Announce Type: cross Abstract: There is significant uncertainty about whether abstractions like beliefs or desires usefully describe the behavior of large language models (LLMs). In
arXiv:2609.05585v1 Announce Type: new Abstract: Robot hands are a key interface between AI and the physical world, making advances in robotic dexterity essential to realizing the vision of physical AI
arXiv:2609.05418v1 Announce Type: cross Abstract: Machine learning training workloads place unique demands on storage systems, yet most existing benchmarks focus on computational throughput rather tha
arXiv:2510.07424v3 Announce Type: replace Abstract: We study linear contextual bandits with paid observations, where at each round the learner observes a context, selects an action, and may pay a fixe
arXiv:2609.07720v1 Announce Type: new Abstract: Long-form narrative-to-film generation requires shot-level controllability and cross-clip consistency in both visual identity and character behavior-req
arXiv:2609.05860v1 Announce Type: new Abstract: Neural operators that accept arbitrary meshes are often treated as geometry-general, but unseen domain topology changes both the invariant and decaying
arXiv:2609.05937v1 Announce Type: new Abstract: Vision Transformers (ViTs) have shown immense potential in medical image analysis. However, standard pre-training via global image classification suffer
An embedded AI/BI dashboard can be securely shared with multiple viewers while ensuring that each viewer can see only their authorized rows. This protection is achieved through group‑based row‑level s
arXiv:2609.08818v1 Announce Type: new Abstract: Person identification from millimeter-wave (mmWave) point clouds has mainly relied on gait. Indoor walking, however, is often brief and interrupted, whi
arXiv:2609.06076v1 Announce Type: new Abstract: Retraining-free MoE compression reduces deployment memory by pruning or merging experts, but often treats the compressed checkpoint as the final artifac
arXiv:2609.07126v1 Announce Type: cross Abstract: In world model planning, sensing inputs pass through an encoder and predictor before affecting planner decisions, so final task success alone cannot r
arXiv:2609.07597v1 Announce Type: new Abstract: Muon can be interpreted as optimizing a linear local objective over a spectral-norm ball. This gives a matrix-sign update that preserves the singular di
arXiv:2609.05535v1 Announce Type: new Abstract: Verdict-only evaluation does not reveal whether a vision-language model (VLM) used the visual evidence that should support its decision. We study this p
arXiv:2609.06394v1 Announce Type: cross Abstract: Massive datasets in modern machine learning have made data reduction a central challenge, particularly for clustering tasks where memory and computati
arXiv:2609.06511v1 Announce Type: new Abstract: Physical and synthetic models may describe complementary aspects of the same PDE-governed system while receiving different, possibly fragmented, observa
arXiv:2604.06589v2 Announce Type: replace Abstract: Bimanual dexterous grasping is a fundamental and promising area in robotics, yet its progress is constrained by the lack of comprehensive datasets a
arXiv:2609.08673v1 Announce Type: new Abstract: Advances in tactile sensing have made contact-rich perception possible, accelerating progress in robotic manipulation, material understanding, and embod
arXiv:2609.05730v1 Announce Type: new Abstract: Contrastive Language-Image Pretraining (CLIP) is a building block of many machine learning applications. Scaling laws have guided resource allocation fo
arXiv:2609.06837v1 Announce Type: cross Abstract: Embodied artificial intelligence has historically very much relied on visual perception, leading to a proliferation of multiple vision-centric world m
Tool: .blend URL Viewer I'm continuing to have a lot of fun with GPT-6 Astra and Blender (see my TIL). As a big fan of the Imperial Fabergé Easter eggs, I've always thought it would be fun to make som
arXiv:2609.07362v1 Announce Type: cross Abstract: Converting in-service reinforced-concrete (RC) building blueprints into simulation-ready models---structured frame representations that support determ
arXiv:2609.07939v1 Announce Type: new Abstract: We address the problem of discovering repeated elements from a single image. In contrast to existing approaches that depend on large annotated datasets,
arXiv:2609.08167v1 Announce Type: new Abstract: Timestamp-supervised action segmentation aims to segment and classify actions in untrimmed videos with a random frame annotated per action. Precisely lo
arXiv:2505.09829v2 Announce Type: replace Abstract: Data scarcity is a primary bottleneck in 3D medical image segmentation: expert voxel-level annotations are expensive, and privacy regulations often
arXiv:2609.08069v1 Announce Type: new Abstract: The learning-rate schedule is a consequential choice in training deep networks, yet the policies in common use are heuristic, and published comparisons
arXiv:2609.06218v1 Announce Type: new Abstract: Automatic skeleton generation involves predicting both joint positions and skeletal connectivity. However, existing approaches struggle to encode branch
arXiv:2609.08220v1 Announce Type: new Abstract: Large language models (LLMs) have recently emerged as a promising tool for automating robot design from high-level specifications, yet they remain ineff
arXiv:2609.05881v1 Announce Type: cross Abstract: Developers increasingly run large language models locally by pulling quantized GGUF artifacts from public registries, yet nothing in the distribution
arXiv:2609.05862v1 Announce Type: new Abstract: Learning on dynamic graphs is difficult when changes in the underlying network are only partially observed. Acquiring current graph information incurs o
Omarchy is a keyboard-first Linux desktop built on Arch and Hyprland by David Heinemeier Hansson (DHH), and its production pipeline, packaging builds, PR review agents, and QA testing, now run on Digi
arXiv:2609.06273v1 Announce Type: new Abstract: Bundle length B is commonly fixed when configuring multi-task multi-robot task allocation (MRTA) algorithms. MinSum and MinMax are known to favor differ
arXiv:2609.06008v1 Announce Type: cross Abstract: We present Cadence, an error-bounded lossy compressor for numeric time series pairing a 330M-parameter time-series foundation model (Google TimesFM-3)
arXiv:2609.06060v1 Announce Type: new Abstract: Long-term electricity-consumption profiles exhibit several simultaneous periodic structures, including daily, weekly, and annual cycles. This work intro
Christine Mui / Politico: California Gov. Gavin Newsom signs into law two bills, backed by Anthropic and OpenAI, regulating how outside groups evaluate AI for safety — SAN FRANCISCO — California Gov.
arXiv:2609.08250v1 Announce Type: cross Abstract: How far a pushed object slides depends on its mass and friction, which no single image reveals. Pretrained visual encoders are increasingly used as th
arXiv:2609.05884v1 Announce Type: new Abstract: Conventional federated learning relies on parameter averaging, which forces clients to be doubly homogeneous: all must run an identical architecture, an
arXiv:2609.07430v1 Announce Type: new Abstract: How robot body configuration shapes human intervention during approach remains underexplored. We conducted a within-participants study with 41 participa
arXiv:2609.06504v1 Announce Type: new Abstract: Memory facilitates question answering over long videos by extracting and retrieving facts to fit within the limited context windows of multimodal LLMs (
arXiv:2609.06434v1 Announce Type: cross Abstract: Can people distinguish between human and AI agency in humanoid teleoperation? To explore this question, we developed extit{Ghost-in-the-Loop}, a teleo
CancerBench: the frontier model cancer cure benchmark. AI lab CEOs keep talking about curing cancer, so I made a benchmark. One metric: how many types of cancer has your model cured? All models are cu
arXiv:2609.09124v1 Announce Type: new Abstract: Visual encoders construct a representation of the image input for Vision-Language models. How much conceptual, as opposed to immediately visible, inform