b11405
cuda: tile the lightning indexer over keys and tokens for 4 heads (#29901) cuda: tile the lightning indexer over keys and tokens for 4 heads With too few heads for a wmma tile, a block scores 64 keys
Knowledge catalogue
cuda: tile the lightning indexer over keys and tokens for 4 heads (#29901) cuda: tile the lightning indexer over keys and tokens for 4 heads With too few heads for a wmma tile, a block scores 64 keys
webgpu: add MMVQ support for Q1_0/Q5_0/Q5_1/Q3_K/Q5_K/Q6_K/MXFP4 (#29483) add supports for q1/q5/q3_k/q5_k/q6_k/mxfp4 of mmvq path Add K_QUANTS_HANDLING macro to q1_0 of mmvq path Website: https://lla
vulkan : Fix undeclared identifiers when -DGGML_VULKAN_RUN_TESTS=ON (#29912) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/52752005 macOS/iOS: macOS Apple
ggml-cpu : add Q8_0 IME1 matrix kernel for SpacemiT X60 (#28479) ggml-cpu : add Q8_0 IME1 matrix kernel for SpacemiT X60 On the SpacemiT X60, IME matrix acceleration only covered Q4_0/Q4_1/Q4_K. Q8_0
kv-cache: fix restoring mismatched KV cache rotation by saving exact rotation metadata (#28498) kv-cache: save exact KV rotation metadata, reject restoring mismatched rotation tests : move the state r
llama : fix unexpected graph reallocation in the k-pool models (#29958) llama : fix unexpected graph reallocation in the k-pool models Both k-pool models built a graph shape that depends on state the
vulkan: sparse flash attention for quantized K/V (#29639) vulkan: sparse flash attention for quantized K/V Assisted-by: Claude vulkan: single-scan sparse FA index compaction The compaction ran one wor
vulkan: fix stale prealloc_y reuse across flash attention and soft_max (#29591) Assisted-by: Claude Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/52808438
server: reject partial media truncation (#24076) server: reject partial media truncation server: keep only the keep_first fix Drop the mtmd test helper change, which no longer builds since clip_image_
CUDA: Optimize accumulation in mmq for NVFP4 type (#29857) ggml_cuda: optimize accumulation in mmq_vec_dot_fp4_fp4_mma for better performance remove whitespace fix: correct indentation in mma_block_sc
server: support vision input for Clef (#29969) server: support vision input for Clef move input_attn_causal to private extend old server_batch::embd server_batch::token::pos to multi dim nits fix abor
vulkan: fix Flash Attention shmem write out of bounds (#29988) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/52864580 macOS/iOS: macOS Apple Silicon (arm6
llama.cpp : bump version to 0.6.0 (#29997) llama.cpp : bump version to 0.6.0 scripts : update summary prompt (#0) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attesta
hexagon: matmul and flash-atten scalability updates (#29974) hexagon: head-parallel flash_attn partitioning for row-split multicore In row-split mode each core computes its output row shard of every M
hexagon: add pool op support (#29995) hexagon: add pool_2d support hexagon: add pool_1d support hex-pool: dma changes hex-pool: Optimize HTP pooling boundaries and DMA pipelining hex-pool: code cleanu
arXiv:2610.02524v1 Announce Type: new Abstract: Unstructured pruning at extreme sparsity often suffers from representational collapse, causing sharp drops in accuracy. To address this, we study Backbo
arXiv:2610.03035v1 Announce Type: new Abstract: Multimodal learning often suffers from modality imbalance, where the joint optimization process is dominated by a single modality. Existing methods typi
arXiv:2610.02440v1 Announce Type: new Abstract: Contextual bandits require balancing nonlinear reward modeling with online efficiency. Tree ensembles and neural methods capture nonlinearities but requ
Banger paper from Microsoft and colleagues. If you run agents that search a large document collection, this one is worth your time. (bookmark it) They introduce CorpusMap, which resolves recurring ent
arXiv:2610.02638v1 Announce Type: new Abstract: Full-duplex voice agents make many small, closed decisions, which current systems answer by slow autoregressive decoding. We propose DuplexJev, which fe
arXiv:2610.03425v1 Announce Type: new Abstract: Suspicion is an important, yet elusive concept in anti-money laundering and counter-terrorist financing (AML/CFT), which allows for intervention below t
arXiv:2610.03051v1 Announce Type: new Abstract: Social bees are important pollinators that support biodiversity and crop pollination globally and serve as important model systems for collective behavi
arXiv:2610.03141v1 Announce Type: new Abstract: Video multimodal large language models (MLLMs) keep climbing video question answering benchmarks, yet shuffling the frames, masking the segment that sup
arXiv:2610.02730v1 Announce Type: new Abstract: This paper proposes a new functional approximation approach to reduce Bellman error in high-dimensional dynamic programming and Reinforcement Learning p
arXiv:2610.03500v1 Announce Type: new Abstract: Deep tabular generative models are benchmarked on datasets with tens of thousands of rows; clinical datasets have hundreds. We preregistered and ran a s
arXiv:2610.03387v1 Announce Type: new Abstract: Typed decision models return choices or distributions over answer options supplied at request time. Accuracy with complete options does not establish wh
arXiv:2610.03130v1 Announce Type: cross Abstract: Biological literature retrieval systems are often developed and evaluated using broad biomedical corpora and general-purpose search tasks. However, ma
arXiv:2610.02739v1 Announce Type: new Abstract: Agentic Text-to-SQL systems can interact with users to clarify underspecified queries before generating SQL. However, a correct execution result does no
arXiv:2610.03400v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards has substantially advanced multimodal reasoning, yet it remains fundamentally limited by ambiguous token-
arXiv:2610.03014v1 Announce Type: cross Abstract: Large language model (LLM)-based agents increasingly connect model-generated decisions to security-sensitive software capabilities such as command exe
arXiv:2610.03456v1 Announce Type: new Abstract: Drug-target affinity (DTA) prediction is widely used to prioritize candidate compounds before costly experimental screening. DTA models are often compar
arXiv:2610.03196v1 Announce Type: new Abstract: A reinforcement-learning (RL) pipeline for a legged robot is assembled from proxies. A reward stands in for intended behaviour, a curriculum gate stands
arXiv:2610.03099v1 Announce Type: cross Abstract: E-commerce videos are information-dense and frequently compared by consumers evaluating products and merchants assessing marketing strategies. However
arXiv:2610.03526v1 Announce Type: cross Abstract: Explainers for Graph Neural Networks (GNNs) are commonly evaluated by their plausibility, i.e., how well their explanations recover a predefined groun
arXiv:2610.03395v1 Announce Type: new Abstract: Long-horizon tasks with sparse rewards pose an exploration bottleneck for goal-conditioned reinforcement learning: a policy started from the initial sta
arXiv:2511.03756v2 Announce Type: replace-cross Abstract: We present a bifidelity Karhunen--Loeve expansion (KLE) surrogate model for field-valued quantities of interest (QoIs) under uncertain inputs.
arXiv:2506.05766v2 Announce Type: replace Abstract: Retrieval augmented generation (RAG) has shown great power in improving Large Language Models (LLMs). However, most existing RAG-based LLMs are dedi
arXiv:2610.02800v1 Announce Type: new Abstract: Speculative decoding accelerates autoregressive generation by using a lightweight draft to propose multiple tokens for parallel verification. However, e
arXiv:2610.02853v1 Announce Type: new Abstract: Safety heads are lightweight classifiers attached to pretrained language models for flagging harmful inputs before generation. Their empirical detection
arXiv:2610.03615v1 Announce Type: new Abstract: Recent advances in frontier models enable robot manipulation from only a few demonstrations, but high inference latency limits their use for real-time r
arXiv:2610.03193v1 Announce Type: new Abstract: The application of machine learning to dermatology has grown substantially in recent years, moving beyond proof-of-concept studies toward potential appl
In 2026, the question for enterprise AI is no longer whether predictive models can outperform statistical forecasts—that argument is settled. The big question now is how to enable predictive systems t
arXiv:2610.03640v1 Announce Type: new Abstract: Neural network loss landscapes have many symmetries, which are preserved by gradient flow but broken by finite-stepsize stochastic gradient descent (SGD
arXiv:2610.02233v1 Announce Type: cross Abstract: Cross-context KV-cache reuse predicts a shared segment's keys and values under a new prefix instead of recomputing them, and has been reported to do s
arXiv:2610.03162v1 Announce Type: cross Abstract: 3D Gaussian Splatting achieves excellent visual quality with real-time rendering, but at the scale of entire cities it does not fit: a trained model c
arXiv:2610.03112v1 Announce Type: new Abstract: Matching candidates to vacancies is central to recruitment, and a recruiter needs to see why a candidate fits, not only a single opaque relevance score.
arXiv:2610.03142v1 Announce Type: new Abstract: Deep neural networks remain vulnerable to adversarial perturbations, which can distort not only predictions but also confidence scores, undermining unce
arXiv:2603.13856v3 Announce Type: replace-cross Abstract: Building AI systems that can plan, act, and create in the physical world requires more than pattern recognition. Such systems must reason abou
arXiv:2508.04860v2 Announce Type: replace-cross Abstract: Stochastic Gradient Descent (SGD) is a cornerstone of large-scale optimization, yet its theoretical behavior under heavy-tailed noise -- commo
arXiv:2603.13725v2 Announce Type: replace Abstract: Memristor-based analog compute-in-memory (CIM) architectures provide a promising substrate for the efficient deployment of Large Language Models (LL
arXiv:2610.02462v1 Announce Type: cross Abstract: LLM compression reduces inference costs and memory requirements, but selecting a method and configuration remains largely empirical because comparable
arXiv:2610.02647v1 Announce Type: new Abstract: The estimation and analysis of facial expression intensity play a crucial role in affective communication and human-computer interaction. Previous resea
arXiv:2610.02221v1 Announce Type: cross Abstract: Physical Activity (PA) is consistently associated with lower risk of dementia, yet the mechanism linking PA to dementia prevention remain incomopletel
arXiv:2610.03452v1 Announce Type: new Abstract: Causal representation learning for time-series data aims to identify latent states and their causal relations from observations. In this setting, an imp
arXiv:2610.03558v1 Announce Type: cross Abstract: Cephalonauts One is a whole-brain 3 Tesla (3T) functional magnetic resonance imaging (fMRI) dataset recorded while subjects listened to audio podcasts
arXiv:2610.03502v1 Announce Type: cross Abstract: Mechanistic edits (ablations, weight edits, activation steering) are the standard tools for unlearning a harmful capability from a neural network whil
arXiv:2610.02711v1 Announce Type: cross Abstract: Human activity recognition (HAR) from wrist-worn accelerometers is increasingly used for health and behavioral tracking. Yet, most wearable HAR models
arXiv:2610.02666v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models map visual observations and language instructions to continuous robot actions, but a diffusion-based action expert (
arXiv:2610.02330v1 Announce Type: new Abstract: Large language models (LLMs) rely on long-horizon tool invocation sequences for complex tasks, where each invocation can alter the task state and condit
arXiv:2610.03441v1 Announce Type: new Abstract: We present ChromaGS, a method for real-time, language-guided color editing of animatable 3D Gaussian head avatars. Given a trained animatable avatar, us