b10995
vulkan: make MUL_MAT_ID BN/2 tail unconditional (#28923) Use BN/2 as the default for BNover2 and as the disabled fallback for BNover4, and remove the enable gate from the MUL_MAT_ID BN/2 branch. The B
Knowledge catalogue
vulkan: make MUL_MAT_ID BN/2 tail unconditional (#28923) Use BN/2 as the default for BNover2 and as the disabled fallback for BNover4, and remove the enable gate from the MUL_MAT_ID BN/2 branch. The B
chat : force n</think> on reasoning budget end for qwen3-coder (#28869) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/47858837 macOS/iOS: macOS Apple Sili
HIP: broaden MoE ncols_opt tile heuristic on RDNA3.5 architecture (#28935) It's found the MoE ncols_opt tile heuristic needs to be broadened to include the RDNA3.5 architecture. The code change is imp
qwen4exp: add hc ops (#28901) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/47897353 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, Kl
Change max context length for auto-fitting with unified KV (#28849) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/47906437 macOS/iOS: macOS Apple Silicon
rpc : invalidate cached compute graph when a referenced buffer is freed (#24292) The server caches the most recent compute graph per device so that GRAPH_RECOMPUTE can re-execute it without resending
spacemit : fix wrong transpose function for int16 data (#25161) The sizeof(int16_t) branch in permute_transpose_impl calls rvv_transposed_s32_mn_to_nm instead of rvv_transposed_s16_mn_to_nm. This is a
CUDA/HIP: improve access patterns in im2col (#28013) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/47937267 macOS/iOS: macOS Apple Silicon (arm64) macOS A
model : add support for HrmTextForCausalLM (DFM Mimir 1B) (#27625) model : add support for HrmTextForCausalLM (DFM Mimir 1B) HRM-Text runs two transformer stacks (low, high) in an alternating cycle ov
hexagon: accept the zeroed rope probe in supports_op (#28995) llama probes weight placement with a rope where all params are 0, so rejecting n_dims == 0 or freq_base == 0 puts rope_freqs on the CPU. T
hexagon: Support for K-Quants Q4_K and Q6_K (#28994) implement q6k/q4k kernels Squashed from: feat: implement q6k kernel hex-q6k: improve unpack accuracy hex-q4_k: add support for Q4_K kernels Co-auth
Enable CUDA graph for MTP draft (#28549) Improve CUDA graph usage for MTP Rename field Address review feedback Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestatio
TP: fix split state and granularity for fused QKV gemma4, qwen35 (#28965) model: calculate split states for attn_qkv from n_head * n_embd_head_k required for gemma4 with --fuse-qkv, where n_embd is 53
arXiv:2609.16407v1 Announce Type: cross Abstract: On a delivery platform, personalized store ranking greatly influences what users find and order. Unlike digital-only domains, candidate stores are loc
Banger paper from Google Research. This one is on how LLM assistants reason about the people in a user's life. People ask assistants for social advice constantly, and the assistant only hears the user
Banger paper from NVIDIA. It's on the topic of choosing which models go into a multi-agent system. The team compared eight selection strategies, based on size, accuracy, answer diversity and error div
Banger report from Salesforce. Pretty interesting to see more of these custom enterprise models. Salesforce trained the enterprise agent model from the same files it uses to configure agents. Koa star
arXiv:2609.16777v1 Announce Type: new Abstract: As Large Language Models (LLMs) increasingly serve as primary knowledge retrieval interfaces, their robustness against extit{persuasion attacks}---attem
arXiv:2505.12192v2 Announce Type: replace Abstract: Early detection of PD remains particularly challenging in resource-constrained settings, where voice-based analysis has emerged as a promising non-i
Anyone interested in trying out a new inference provider? We're testing Gemma 4:26b and Qwen 3.8:27B behind an OpenAI-compatible API and looking for a few users to give them a spin and tell us how it
arXiv:2609.17065v1 Announce Type: cross Abstract: AI assistance places a metacognitive demand on users, who must judge their own competence and the system's. Yet designers lack comparative evidence on
arXiv:2609.16006v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly serve users whose expectations are shaped by their cultural context, yet most cultural evaluations test what
arXiv:2609.16069v1 Announce Type: cross Abstract: Synthetic tabular data can match real data distributions while still violating the semantic constraints that govern valid tabular rows. This reveals a
arXiv:2609.16752v1 Announce Type: new Abstract: Cognitive Field Theory (CFT) proposes that cognition arises from memory-dressed collective dynamics that generate a persistent macroscopic cognitive fie
arXiv:2609.16518v1 Announce Type: cross Abstract: Capturing hand motion and interaction forces is critical for interactive computing, VR, and high-fidelity tactile demonstrations for robot learning. W
arXiv:2609.17068v1 Announce Type: cross Abstract: Congenital heart disease (CHD) diagnosis and surgical planning often require patient-specific 3D anatomical models, but manual segmentation is labor-i
arXiv:2609.17014v1 Announce Type: cross Abstract: Machine learning (ML) has become the dominant approach for network traffic classification, achieving very high predictive performance. However, a mode
arXiv:2609.16501v1 Announce Type: cross Abstract: De-identified resume screening assumes that redacting explicit fields prevents ethnocultural inference; however, recent audits attribute residual leak
arXiv:2609.16937v1 Announce Type: cross Abstract: On-policy distillation (OPD) has emerged as an effective approach for large language model post-training, yet existing objectives face a trade-off bet
arXiv:2609.17039v1 Announce Type: new Abstract: Sparse-view 3D scene reconstruction with 3D Gaussian Splatting (3DGS) is inherently underconstrained. Plausible renderings can also coexist with erroneo
arXiv:2609.16040v1 Announce Type: new Abstract: Bilateral control-based imitation learning captures both position and force information, making it well suited to contact-rich manipulation. However, ex
arXiv:2609.15995v1 Announce Type: new Abstract: Emerging AI regulation mandates bias audits of high-risk systems, and audit scores are beginning to be used to rank models. Both uses assume different a
arXiv:2609.17477v1 Announce Type: cross Abstract: The absolute capacity of dense associative memory has mainly been analyzed for unbiased patterns. Here we examine the effect of bias in centered binar
arXiv:2603.00156v2 Announce Type: replace Abstract: Medical image segmentation is a cornerstone of computer-assisted diagnosis and treatment planning. While recent multimodal vision-language models ha
arXiv:2609.17067v1 Announce Type: cross Abstract: Indirectly encoded neural networks can assign different activation functions to individual nodes, but the right functions are rarely known in advance.
arXiv:2609.16305v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly operate over long-horizon interactions involving tool use, persistent state, evolving authorization, and
arXiv:2609.16380v1 Announce Type: new Abstract: Class-balanced learning and label noise create a coupled failure mode: frequency correction prevents majority classes from dominating the decision rule,
arXiv:2609.17443v1 Announce Type: new Abstract: Vision-language models (VLMs) achieve strong visual question answering (VQA) performance, but processing large cluttered images is computationally expen
arXiv:2609.17106v1 Announce Type: new Abstract: Detecting and grasping small objects remains a significant challenge in robotics. Active vision, where the robot moves closer to the object, is an intui
arXiv:2609.16338v1 Announce Type: new Abstract: Ternary Large Language Models (LLM) store every weight as one of three symbols {-1,0,+1}, so the cost of a ternary model is conventionally referenced to
arXiv:2609.16884v1 Announce Type: new Abstract: In partially observable settings, agents must act without full knowledge of the world state and rely on uncertain state-estimation pipelines. Obtaining
arXiv:2609.17386v1 Announce Type: new Abstract: Test-time prompt tuning (TPT) enables adaptation on a single test instance, achieving improved accuracy but often sacrificing calibration performance. M
arXiv:2609.17483v1 Announce Type: cross Abstract: Modern large-scale machine learning tasks often require multiple workers, devices, CPUs, or GPUs to compute stochastic gradients in parallel and async
arXiv:2609.16664v1 Announce Type: new Abstract: Leveraging Large Vision-Language Models like CLIP has recently set new benchmarks for No-Reference Image Quality Assessment (NR-IQA). However, the contr
Learn how to automate end-to-end PII detection and redaction from scanned documents at scale using Amazon Bedrock Data Automation with a custom blueprint, AWS Step Functions, and AWS Lambda. A custom
arXiv:2609.17263v1 Announce Type: new Abstract: Assembly Sequence Planning (ASP) remains a challenging problem due to its combinatorial nature, making exhaustive planning approaches impractical for co
Manufacturing artificial intelligence startup CADDi Co. Ltd. today announced it has raised 114 million in new funding at a valuation of 1.2 billion, partly to expand in North America. CADDi builds sof
arXiv:2609.16251v1 Announce Type: new Abstract: Computer-use agents are increasingly evaluated in realistic desktop environments, but existing benchmarks provide limited coverage of professional engin
arXiv:2609.17265v1 Announce Type: cross Abstract: Training multi-agent drone-swarm policies directly in high-fidelity (HF) rigid-body physics is accurate but computationally expensive. This cost scale
arXiv:2609.16206v1 Announce Type: new Abstract: Disaggregated LLM serving places compute heavy prefill and memory heavy decode on separate GPU pools. Systems such as DistServe, Splitwise, and Mooncake
Hey experts! I genuinely have this question and would love a general consensus from people actually using these models. LLMs have advanced a lot in benchmarks and in practical usage. Even GPT-4o and G
arXiv:2609.16853v1 Announce Type: new Abstract: Can deep learning translate physical fields governed by fundamentally different equations? We address this question by introducing Cross-Physics Mapping
arXiv:2609.16637v1 Announce Type: new Abstract: Efficient perception is central to robotic systems operating under constrained computation, memory, and latency budgets. Knowledge transfer from larger
arXiv:2609.16997v1 Announce Type: new Abstract: Crisis sentiment analysis is especially challenging for low-resource languages such as Bangla, where language, context, and public reaction shift rapidl
arXiv:2603.15547v2 Announce Type: replace-cross Abstract: Modeling student misconceptions in a realistic manner is critical for AI in education. In this work, we examine how large language models (LLM
arXiv:2609.16814v1 Announce Type: new Abstract: While Large Language Model (LLM)-based Natural Language Inference (NLI) systems achieve high accuracy, their decision-making processes lack auditable st
arXiv:2609.17434v1 Announce Type: cross Abstract: Family caregivers of people living with dementia shoulder emotional and practical responsibilities, yet their own wellbeing often remains peripheral t
arXiv:2609.16742v1 Announce Type: cross Abstract: Convolutional Neural Networks (CNNs) are increasingly deployed in safety-critical edge applications, where soft errors can silently corrupt inference
arXiv:2609.16890v1 Announce Type: new Abstract: Large Language Model (LLM) unlearning is essential for removing sensitive or copyrighted knowledge while preserving general utility. Existing methods of
arXiv:2609.16017v1 Announce Type: cross Abstract: Time-of-flight non-line-of-sight (NLOS) imaging recovers information from hidden objects by analyzing the time of flight of indirect photons scattered