b10771
mtmd: add mtmd_tokenize_from_parts() (#28250) add mtmd_tokenize_from_parts use it in mtmd-cli move add_special to call level Website: https://llama.app Attestations: https://github.com/ggml-org/llama.
Knowledge catalogue
mtmd: add mtmd_tokenize_from_parts() (#28250) add mtmd_tokenize_from_parts use it in mtmd-cli move add_special to call level Website: https://llama.app Attestations: https://github.com/ggml-org/llama.
ggml-hexagon: add F16 support for unary ops (#28228) Extend the HTP backend's F16 unary op coverage to include ABS on top of the existing NORM/RMS_NORM/L2_NORM/SCALE/CLAMP/SQR/SQRT set. Add hvx_abs_f1
server : accept data: URLs for input_video and input_audio (#27735) server : accept data: URLs for input_video and input_audio input_video and input_audio passed accept_base64_uri=false to handle_medi
finetune: fix no KV cache (#27199) training: fix no KV cache apply @ ggerganov suggestion Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/44871971 macOS/iOS
mtmd: fix idefics3 preproc (#28273) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/44875193 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm
model: add NVIDIA Nemotron-3-Puzzle-75B-A9B (NemotronHPuzzle) support (#25444) hparams: add per-layer n_ff_exp/n_expert_used arrays with scalar-or-array loading G1/G2 infrastructure for variable-per-l
sycl: reduce redundant work in Q4_K multi-column MMVQ (#27062) sycl: Q4_K Weight unpack optimization and reuse between destination Columns sycl: Q4_K small N (N=2..4) + two output rows by subgroup reu
misc : prevent RAM peaking at model loading stage (#27483) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/44939788 macOS/iOS: macOS Apple Silicon (arm64) m
sycl : enhance the api to support peer-to-peer copy (#27550) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/44948405 macOS/iOS: macOS Apple Silicon (arm64)
vulkan: fix FA dequant path engagement (#28190) Skip the nb[3] check when ne[3] == 1, the shader never reads it for a single stream. Cache views carry the full-buffer stride there, so the old check re
CUDA: Allow concurrent streams per split for multi-GPU (#28198) CUDA: Allow CUDA optimization per split for multi-GPU. Previous guard caused multi-GPU to skip the graph optimization. The graph is alre
mtmd : add const in various places (#28307) mtmd : mark context as const in more methods Mark mtmd_context as const in: mtmd_bitmap_init_lazy mtmd_tokenize mtmd_tokenize_from_parts mtmd_helper_support
metal : fix glu dispatch with ne00 = 1 (#28306) metal : fix glu dispatch with ne00 = 1 tests : disable ill-defined tests Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/
metal : add sparse FA (#28098) metal : support n_kv_max sparse mask hint in flash attention vec kernel add kernel_flash_attn_ext_vec_idx: compacts finite mask entries into a per-row index list (Hillis
mtmd: propagate const to preproc class (#28310) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/44990064 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple
tune MMVQ to MMQ crossover for SM87 (#28285) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/45087167 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Sil
opencl: quant lm_head / decode GEMV and medium-batch GEMM optimizations (speculative decoding/MTP) (#26477) opencl: quant lm_head / decode GEMV and medium-batch GEMM optimizations opencl: guard q4_K/q
common/json-schema : fix GBNF grammar generation for empty object schemas (#28279) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/45102223 macOS/iOS: macOS
llama: fix whole source code rebuilt on each new commit (#28278) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/45114012 macOS/iOS: macOS Apple Silicon (ar
arXiv:2606.21052v2 Announce Type: replace-cross Abstract: Speech Emotion Recognition (SER) systems increasingly leverage self-supervised acoustic representations, yet their vulnerability to training-t
arXiv:2609.02748v1 Announce Type: new Abstract: Natural images follow a 1/f^2 spectral distribution: most signal energy lies in the low spatial frequencies, while the perceptually important structures
Banger paper from BAAI. If you are building research agents, this one is worth your time. (bookmark it) They find that adding skills scores 134.3% higher on MLE-bench, 34.4% higher on PaperBench, 9.2%
Banger paper from Google DeepMind and colleagues. (bookmark it) A model reads its entire KV cache on every generated token, even though it ends up attending to a tiny slice of it. In other words, if y
arXiv:2609.01914v1 Announce Type: cross Abstract: Reliable attractor recall conventionally requires broad basins of attraction. However, in reservoir-computing based associative memory, temporal cues
arXiv:2609.02304v1 Announce Type: new Abstract: A fundamental quantity in machine learning is the optimal performance achievable by any model on a given task. Estimating this quantity allows us to dis
arXiv:2609.02512v1 Announce Type: new Abstract: Beauty assessments from Multimodal Large Language Models (MLLMs) are increasingly popular amongst users, companies, and aestheticians. This raises the q
arXiv:2609.02414v1 Announce Type: cross Abstract: Multi-turn jailbreak attacks demonstrate that harmful intent can be distributed across dialogue, yet existing methods obscure what conversational mech
arXiv:2609.01861v1 Announce Type: new Abstract: The performance of an LLM agent depends on the scaffold around a frozen model. A common way to improve that scaffold is to use a coding agent as an opti
Benchmarking AI systems is a continual process that co-evolves with the models. New benchmarks challenge AI capabilities with emerging questions to shape the directions and feedback signal of the rese
arXiv:2609.01982v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as assistants for statistical and data science work, yet existing evaluations largely assume the anal
arXiv:2609.02831v1 Announce Type: new Abstract: Modern cameras transform RAW sensor measurements into sRGB images through an image signal processor (ISP). We benchmark two placements for blind restora
Learn best practices for building production-grade, agent-based business process automations with Amazon Quick Automate: choosing the right process, designing focused agents, combining them with deter
I am working with multi-language content and have so far been useing gemma4:e2b for general work. Today I tried it with Russian for the first time and the result was not great. Gemma4:e4b was better,
arXiv:2605.25784v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) have advanced rapidly in remote-sensing analysis, yet existing evaluations remain predominantly 2D-centric.
arXiv:2609.02129v1 Announce Type: new Abstract: Data-centric agents repeatedly perform a discovery step before planning or execution: identifying the data objects relevant to a task. Yet successful di
arXiv:2601.07468v2 Announce Type: replace Abstract: Memory enables Large Language Model (LLM) agents to perceive, store, and use information from past dialogues, which is essential for personalization
arXiv:2609.02152v1 Announce Type: cross Abstract: Multimodal Recommender Systems (MRSs) typically rely on a flawed 'modality harmony' assumption, presuming that multimodal features are inherently bene
arXiv:2609.02092v1 Announce Type: new Abstract: LLM-based multi-agent systems (MAS) are increasingly considered for high-stakes decision-making, yet outcome-based fairness audits can miss where risks
arXiv:2410.10136v2 Announce Type: replace-cross Abstract: In customer contact centers, human agents often struggle with long average handling times (AHT) due to the need to manually interpret queries
arXiv:2609.01659v1 Announce Type: cross Abstract: Chain-of-thought (CoT) reasoning powers generative models by eliciting intermediate steps before producing an answer. In autonomous driving, the answe
arXiv:2609.02750v1 Announce Type: new Abstract: Multi-agent LLM systems commonly use an orchestrator to decompose a task for a team of workers and then improve through textual reflection. Despite stro
arXiv:2606.18069v2 Announce Type: replace-cross Abstract: A surface representation suitable for geometry processing should be compact and explicit, provide global smoothness guarantees, support a wide
arXiv:2609.02502v1 Announce Type: cross Abstract: Text-to-image (T2I) models have achieved remarkable success at faithfully rendering specified objects and attributes, yet their ability to produce vis
arXiv:2609.02172v1 Announce Type: new Abstract: Optimization-based jailbreak attacks such as Greedy Coordinate Gradient (GCG) achieve strong effectiveness and transferability by optimizing adversarial
BREAKING: It’s been revealed NVIDIA's $12,930,300,000.00 acquisition of Hugging Face contains an easter egg. The first 6 numbers of the acquisition price represent the decimal conversion of Unicode ch
arXiv:2603.06698v3 Announce Type: replace Abstract: Knowledge distillation between asymmetric architectures often induces severe geometric constraints on the learned representation space. We investiga
arXiv:2602.22453v3 Announce Type: replace Abstract: Recent work has identified a subset of attention heads in Transformer as retrieval heads, which are responsible for retrieving information from the
Brilliant paper on long-horizon agents. They cut 78.9% of an agent's LLM calls while raising its success rate. Here is how: It turns out that ReAct issues one primitive action per model round. That al
AI factory management is expanding beyond software and servers to encompass the physical systems supporting production workloads. Broadcom Inc. and Super Micro Computer Inc. are integrating their tech
arXiv:2609.02131v1 Announce Type: cross Abstract: Sentiment in social-media threads does not only vary across posts; it shifts as users react to claims, corrections, evidence, and hostility within a b
arXiv:2609.02401v1 Announce Type: new Abstract: Autoregressive vision language models unify heterogeneous perception tasks but are highly susceptible to compounding errors. On-policy distillation (OPD
arXiv:2609.02450v1 Announce Type: new Abstract: Semantic triggers in federated learning (FL) can be less conspicuous than synthetic patches, but sample-dependent placement may weaken backdoor implanta
arXiv:2609.01991v1 Announce Type: new Abstract: Magnetic core loss originates in the hysteresis loop: the energy dissipated per excitation cycle equals the loop area, and frequency, temperature, and w
I've been building Arcon around Qwen3-4B + LoRA. Instead of just making it a chatbot, I'm experimenting with persistent memory, personality/mood, internal state, tools, and eventually having it proces
Can a strong general-purpose vision model distinguish real from AI-generated images using only a simple decision rule on frozen representations? Our latest results, to be presented at #ECCV2026, show
arXiv:2609.01833v1 Announce Type: new Abstract: Sentence-level recognition of depression symptoms is challenging because similar expressions can differ in symptom relevance, and language-model inferen
arXiv:2510.20820v4 Announce Type: replace Abstract: Existing personalized image generators still struggle to preserve multiple reference identities in natural and coherent multi-human generations. To
Agentic artificial intelligence security startup Capsule Security Ltd. today released a detection system built on two Nvidia Corp. Nemotron models it fine-tuned itself, in what it calls an “AI circuit
arXiv:2609.02265v1 Announce Type: new Abstract: Personalized language agents use persistent memory to adapt to users over time, but the same mechanism creates an attack surface. When new information c
arXiv:2510.07177v2 Announce Type: replace Abstract: Aspect-based summarization has attracted significant attention for its ability to generate more fine-grained and user-aligned summaries. While most