Knowledge catalogue
arXiv:2609.25961v1 Announce Type: new Abstract: Generative visual models offer a foundation for learning representations of physical dynamics, yet their extension to continuous control raises a fundam
arXiv:2609.25634v1 Announce Type: new Abstract: We trained 64 independently seeded networks in four configurations, continuing each to sustained convergence or a 40,000-epoch ceiling. We then asked wh
arXiv:2609.25731v1 Announce Type: new Abstract: Medium-resolution (10-30 m) burned area mapping is vital for monitoring wildfires and their impacts, but remains difficult to scale. Existing methods re
Robert Hart / The Verge: Anthropic says Claude autonomously discovered a new enzyme system in the DNA of bacteriophages, somewhat similar to CRISPR, the first result from its new biolab — It took near
Anthropic says its AI Claude has 'autonomously discovered' a new enzyme system similar to machinery behind the powerful gene-editing tool Crispr. It's the first result from Anthropic's newly-launched
arXiv:2609.24165v1 Announce Type: new Abstract: Synchrotron data reduction, detector calibration followed by azimuthal integration of terabyte-scale diffraction series, is a multi-step, expert-bound b
https://huggingface.co/bartowski/LensVLM-9B-GGUF LensVLM-9B LensVLM is a 9B Vision Language Model (VLM) that scans compressed images of text, then selectively expands only the relevant pages to their
Todd Bishop / GeekWire: At its Accelerate conference, Amazon says it is opening its seller tools to third-party AI agents, starting with Claude, in beta for US merchants — Amazon announced new AI tool
Yep. I just need tips honestly on UI layouts and how to build my shell for the local api offline. I’m using qwen and ollama and just want a simple discord style interface to declutter my brain to like
arXiv:2609.25808v1 Announce Type: cross Abstract: Evaluation scores are often validated by their agreement with inexpensive proxy labels. When the score and the proxy are computed from the same text s
arXiv:2609.25914v1 Announce Type: new Abstract: Complex-valued neural networks (CVNNs) are increasingly adopted for complex-valued data; however, they are often trained with first-order optimizers inh
arXiv:2609.26748v1 Announce Type: cross Abstract: Clustering is an unsupervised learning technique that partitions unlabeled data into groups. Most existing methods require user-specified parameters,
HIP : optimize IQ2/IQ3 (__vsub4 __vcmpne4) using SWAR (#27962) HIP : use bit manipulation for __vcmpne4 HIP : use bit manipulation for __vsub4 Website: https://llama.app Attestations: https://github.c
hex-dma: introduce direct-mapped DMA cache that is better suited for HVX FA mask handling (#29282) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/49404271
sampler: reduce the size of the probe (#29285) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/49443624 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple S
vulkan: hide internal symbols to prevent duplicate-dlopen state destruction (#29139) Since #28732 our internal symbols are exported. A duplicate copy dlopened and dlclosed by ggml_backend_load_all() t
sycl : support op get_rows_back, only support fp32/fp16 (#25266) resovle confict support gedt_rows_back, update the ops.md Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cp
sycl: extend MMVQ GLU fusion, add rms_norm+scale and ssm_conv+silu fusions (#28931) sycl : extend MMVQ GLU fusion to mixed quant types; add rms_norm+scale and ssm_conv+silu fusions fixing spacing issu
sycl : support new UT case for mul_mat_hadamard fp16 (#29218) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/49484593 macOS/iOS: macOS Apple Silicon (arm64
cuda: top-k MoE should always fire (#28432) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/49495074 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Sili
ggml-meta: resolve multi buffer views (#29266) ggml-meta: resolve multi buffer views add TODO to revisit if graph allocator gets refactored Website: https://llama.app Attestations: https://github.com/
vulkan: add IQ4_XS MMQ/MMV matmul kernels (#28415) vulkan: optimize IQ4_XS matmul kernels Assisted-by: OpenAI Codex vulkan: address IQ4_XS review nits drop the dead LOAD_VEC_A != 8 branch in the IQ4_X
make-release : update summary prompt Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/49525233 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (ar
model : support Gemma4 DSpark draft backbone (#29226) dspark: add Gemma 4 draft support Add GGUF conversion and runtime support for full-attention and SWA Gemma 4 DSpark drafts, including tied output
server: Dedup the draft HF model via dedup-cache-models (#27934) server: Dedup the draft HF model via dedup-cache-models Fixes #27846 server: avoid capturing structured binding in lambda Website: http
server: accept OpenAI video_url content type and data: video URIs (#27921) The OpenAI chat completions API specifies content part type 'video_url' with a {'url': ...} object, and clients typically sen
jinja : parse unary +/- before variables (#29244) jinja : parse unary +/- before variables Lexer already emits unary_operator for -n / +n, and runtime executes unary -. Parse them at multiplicative pr
server: fix token counting API crash on sleep (#29309) server: wake up sleeping server correctly server: wake up sleeping server correctly (local aliases removed) Website: https://llama.app Attestatio
CUDA: enable sparse-fa for dsv4 prefill (again) (#29298) CUDA: enable sparse-fa for dsv4 prefill (again) CUDA: unroll the query loop of the sparse mask scan The query loop of flash_attn_mask_to_sparse
llama.cpp : bump version to 0.5.0 (#29333) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/49623059 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silic
opencl: add A8 Q6_K non-MoE dp4a binary kernel (#29057) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/49630180 macOS/iOS: macOS Apple Silicon (arm64) macO
tests: add -b/--backend option to test-llama-archs for testing a specific backend (#27372) tests: add backend option to test-llama-archs Update tests/test-llama-archs.cpp Co-authored-by: Johannes Gäßl
arXiv:2609.24921v1 Announce Type: new Abstract: Scientific weak signals are early, low-visibility research directions that later become central to mature scientific topics, yet existing resources such
arXiv:2609.25040v1 Announce Type: cross Abstract: Banana crop diseases threaten food security across the world, yet field diagnosis remains difficult because of limited expert access and visual simila
Banger paper from Stanford and Together AI. They show why it might be a good idea to let your agent team learn its own way of working together. (bookmark it) Three models (o3-mini, Claude Sonnet 4 and
arXiv:2410.07421v2 Announce Type: replace Abstract: Instance segmentation is a core computer vision task with great practical significance. Recent advances, driven by large-scale benchmark datasets, h
arXiv:2609.24663v1 Announce Type: new Abstract: Self-evolving agents convert interaction feedback into persistent artifacts, such as memories or skills, which in turn guide subsequent decisions. As th
arXiv:2609.25007v1 Announce Type: cross Abstract: The performance of state-of-the-art speaker verification (SV) systems severely degrades on short utterances due to insufficient speaker-specific infor
arXiv:2609.26208v1 Announce Type: new Abstract: Data visualization is central to analytical reasoning, but real-world analysis increasingly requires language-driven interactive interfaces rather than
arXiv:2503.15242v3 Announce Type: replace Abstract: We introduce BigO(Bench), a novel coding benchmark designed to evaluate the capabilities of generative language models in understanding and generati
arXiv:2609.26147v1 Announce Type: new Abstract: Modern LLMs are deployed as families of post-trained variants (base, instruct, chat, code) derived from a shared set of pre-trained weights. We present
arXiv:2609.22696v1 Announce Type: new Abstract: Decentralized social media platforms create new opportunities and challenges for computational mental health research because data access, moderation, l
arXiv:2609.25693v1 Announce Type: new Abstract: Object detection in adverse weather remains challenging because severe degradations weaken visual quality and disrupt semantic feature representations a
arXiv:2609.25606v1 Announce Type: new Abstract: Cable routing requires coordinated control of global cable topology and changing local contacts. We present CableVLA, an end-to-end multimodal vision-la
arXiv:2609.25814v1 Announce Type: new Abstract: Dynamic graphs are widely used to model time-evolving relational systems in real-world applications. Dynamic graph neural networks provide an effective
arXiv:2609.25138v1 Announce Type: cross Abstract: Calibration count reuse raises separate validity and efficiency questions. We give a validity criterion for general count-dependent nonconformity scor
arXiv:2609.26242v1 Announce Type: new Abstract: When a data license expires, deleting stored records does not remove influence encoded in a trained forecaster. Machine unlearning seeks to remove this
Can you take the cheapest open model from a frontier lab & beat closed models on the hardest long range tasks? Yep Our open adaptive intelligence system Zenith ramps DeepSeek v4.1 Flash past GPT 5.6 S
arXiv:2609.26637v1 Announce Type: new Abstract: The rapid capability gains of frontier language models are widely attributed to improved reasoning abilities, yet this cannot be verified as raw CoT tra
arXiv:2609.25938v1 Announce Type: cross Abstract: A conformal abstention certificate for text-to-SQL is only as truthful as the correctness labels it is calibrated on. The uncertainty pipelines that r
arXiv:2609.25058v1 Announce Type: new Abstract: Parameter-efficient fine-tuning (PEFT) adapts large language models (LLMs) to downstream tasks while updating only a small fraction of their pretrained
arXiv:2511.17909v2 Announce Type: replace Abstract: Chemical reasoning inherently integrates visual, textual, and symbolic modalities, yet existing benchmarks rarely capture this complexity, often rel
arXiv:2604.07733v2 Announce Type: replace Abstract: Evaluating strategic decision-making in LLM-based agents requires generative, competitive, and longitudinal environments, yet few benchmarks provide
Claude has discovered a previously unknown enzyme system hidden in the DNA of bacteriophages. Beside the enzyme’s gene sits a long array of repeating DNA—a structure that looks somewhat similar to CRI
arXiv:2609.26779v1 Announce Type: cross Abstract: Agents often work on complex problems that require millions of tokens of context, which necessitates compacting across sessions due to limited context
arXiv:2609.25453v1 Announce Type: new Abstract: Medical image analysis remains fundamentally challenging because of the intricate geometric and topological structures present in medical data. Conventi
arXiv:2609.26399v1 Announce Type: new Abstract: Scene safety understanding plays a life-or-death role in situational awareness in various critical domains. Traditional methods that rely on learning di
arXiv:2608.28021v2 Announce Type: replace-cross Abstract: Large language models increasingly author Infrastructure-as-Code (IaC), where one insecure default is provisioned straight into production. Pr
arXiv:2609.26173v1 Announce Type: new Abstract: Many post-training quantization (PTQ) methods use layer-wise reconstruction, second-order proxy objectives, or activation-aware transformations to reduc
arXiv:2609.25537v1 Announce Type: new Abstract: Large language model (LLM) inference is constrained by the quadratic scaling of self-attention and the linear scaling of the KV cache, increasing latenc