All entries

arXiv:2609.36373v1 Announce Type: cross Abstract: A personal language agent that acts for its owner across private and shared conversations can learn a fact from one audience and later place it in the

arXiv:2609.38021v1 Announce Type: cross Abstract: We evaluate an auditable long-term memory system on LongMemEval-S. Its retrieval chain uses hybrid candidate retrieval, cross-encoder reranking, cover

arXiv:2609.37474v1 Announce Type: new Abstract: Persistent memory creates a control problem that retrieval relevance alone does not solve: a memory can remain highly useful after an update, deletion,

arXiv:2609.37616v1 Announce Type: cross Abstract: Language models tend to agree with whatever a user asserts, and post-training increasingly targets this sycophancy so that models evaluate claims on t

arXiv:2609.36662v1 Announce Type: cross Abstract: The pre-training of Large Language Models (LLMs) is increasingly conducted across multiple data centers. As training scales to a larger number of acce

arXiv:2609.37310v1 Announce Type: cross Abstract: With LLM watermarking being deployed commercially and now required by regulations, improving its reliability and effectiveness has become crucial. Yet

arXiv:2609.35812v1 Announce Type: new Abstract: In-car conversational assistants (ICAs) are increasingly integrated into vehicles to support route planning, vehicle control, and information access. En

arXiv:2609.36847v1 Announce Type: new Abstract: Percutaneous iliosacral screw fixation is an important minimally invasive treatment for unstable pelvic fractures. Because the sacroiliac region has com

arXiv:2609.36503v1 Announce Type: new Abstract: Adding or removing a sounding object requires coordinated changes to visual content and sound while preserving the surrounding scene. Yet paired supervi

arXiv:2609.34951v2 Announce Type: replace Abstract: In 2023, AI models answered from training data and hallucinated when it ran out, and businesses were told to seed that knowledge. Models' training k

vulkan: Tune GDN kernel, fix Intel performance (#29476) vulkan: tune GDN shader tune for Intel Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/51306598 macO

opencl: fix get_tensor for q5_K adreno gemm_nonshuffle kernel (#29555) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/51311810 macOS/iOS: macOS Apple Silic

ci: add zdnn backend build but not test (#29541) ci: add zdnn backend build but not test Signed-off-by: Aaron Teo aaron.teo1@ibm.com ci: attempt to run a ubuntu 26.04 container Signed-off-by: Aaron Te

ggml-cuda: HIP: optimize packed byte subtraction (__vsubss4 -> __vsub4) (#29478) ggml-cuda: HIP: optimize non-saturating packed byte subtraction (__vsubss4) CI: ignore 1 spilled vgpr in fattn_vec Co-a

hexagon: optimize concat op (#29673) hex-concat: reduce pkts in gather/transpose hot loop gather directly into dst buffer, use special instruction for gather sync hex-concat: use fastdiv replace calls

model : support classifier_pooling for rerankers (#29627) model : support classifier_pooling for ModernBERT rerankers Assisted-by: Claude Opus 5.5 model : read classifier pooling type in load_hparams

ggml : check row bounds in get_rows_back (#29575) Signed-off-by: Adrien Gallouët angt@huggingface.co Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/5139241

gguf : reject tensor size that wraps after padding (#26979) GGML_PAD(nbytes, alignment) wraps to 0 when nbytes is within (alignment - 1) of SIZE_MAX, which silently bypassed the size overflow guard in

Hexagon f16 activation ops (#29209) hexagon: add F16 support for activation ops (SILU/GELU/GELU_QUICK/GEGLU/SWIGLU) Widens ggml_hexagon_supported_activations() to accept F16 (src0/dst/src1 must agree

ggml-zdnn: impl buffer reset, fix memory leaks (#29637) cont: fix code style Signed-off-by: Aaron Teo aaron.teo1@ibm.com Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/

vendor: update BoringSSL to 0.20260929.0 (#29669) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/51432581 macOS/iOS: macOS Apple Silicon (arm64) macOS Appl

add GLM-5.3-Flash (GLM5-Next) support (#27773) Rebase GLM-Next support onto master, and migrate to llama-memory-hybrid-idx Add initial MTP support Merge branch optimizations. Reduce allocated compute

SYCL: reduce tensor allreduce sync with pinned host buffers (#29604) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/51446793 macOS/iOS: macOS Apple Silicon

musa : define CUDA_ARCH for device passes (#29508) The MUSA vendor header never defined CUDA_ARCH, so every architecture test in the shared ggml-cuda sources evaluated to 0. Kernel bodies gated on the

openvino: serve GET_ROWS on a weight view from the base Constant (#28381) openvino: serve GET_ROWS on a weight view from the base Constant Resolve view_src when collecting weight Constants so a view o

cpu: accept BF16 in src1 of mul_mat (#28937) cpu: accept BF16 in src1 of mul_mat ggml_conv_1d_dw builds its im2col in F32 when the kernel is BF16, then calls ggml_mul_mat(im2col, kernel), which puts F

ggml : add BF16 unary, GLU, binary and scale ops (CPU, CUDA) (#29675) ggml : add BF16 unary, GLU, binary and scale ops (CPU, CUDA) ggml-cpu : use per-op _bf16 functions for BF16 unary and GLU ops Assi

llama: llama_prefetch_rows (#29599) llama: llama_prefetch_rows llama: support row prefetch on Windows Apply the Windows port contributed by @praneshgo unchanged. Source: #29599 (comment) avoid exposin

ci : fix Models Backend Check by shortening the hrm_text fixture (#29744) The fixture recycles its two blocks over 8 cache slots, so the fp16 error builds up past the 1e-4 NMSE bound on the Vulkan T4

jinja : support coerced array attributes (#29574) support coerced array attributes add tests Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/51590476 macOS/

mimo : support dflash (convert + feature extraction) (#29650) convert : update to support dflash cont : fix Co-authored-by: Sigbjørn Skjæret sigbjorn.skjaeret@huggingface.co Co-authored-by: Sigbjørn S

cli: exit on stdin EOF and drop the console wide Ctrl+C broadcast (#29722) cli: exit on stdin EOF and drop the console wide Ctrl+C broadcast On Windows the simple input reader sends CTRL_C_EVENT to ev

ggml/gguf : fix integer overflow (#29384) ggml: fix integer overflow guard for zero-element tensors ggml: validate number of elements in tensor to prevent integer overflow ggml: fix error print Websit

glm5-next: give dead indexer slots unique scatter rows (#29745) The sparse indexer mask is built with a set_rows scatter. Padded pools, absent sequences and missing tail cells all pointed to the same

batch: migrate the rest of examples to llama_batch_ext (#29601) migrate the rest test-thread-safety rm common_batch_staged Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cp

llama: properly handle KV on training (#28520) llama: properly handle KV on training improve Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/51644581 macOS/

test-llama-archs : toggle causal_attn to catch graph shape changes (#29724) After the device decode, flip causal_attn off, decode n_ubatch/2 then n_ubatch tokens. Both have the same node count, so a s

'AREX-2 is a 27B-parameter long-horizon agent model from the Beijing Academy of Artificial Intelligence (BAAI). It learns to improve a solution over multiple test-time rounds: propose, measure, reflec

arXiv:2609.37016v1 Announce Type: new Abstract: Structured images, such as diagrams, charts, and flowcharts, are inherently symbolic and can be compactly represented in an editable format, yet in prac

arXiv:2609.37468v1 Announce Type: cross Abstract: Agentic retrieval-augmented generation (RAG) interleaves reasoning with repeated retrieval, giving the retriever influence over both the evidence an a

arXiv:2609.37367v1 Announce Type: cross Abstract: Decentralized large language model (LLM) fine-tuning lets organizations collaboratively train a shared LLM on data they cannot pool, without a central

arXiv:2609.36738v1 Announce Type: cross Abstract: Optimizer momentum is usually stored as a parameter-sized moving average of past gradients, which makes history costly and fixes each past signal in t

arXiv:2406.00083v3 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by retrieving relevant information from external knowledge bases to

arXiv:2609.36913v1 Announce Type: cross Abstract: Transcribing domain-specific entities and rare proper nouns remains a major challenge in automatic speech recognition (ASR). In this paper, we propose

arXiv:2609.35877v1 Announce Type: cross Abstract: Many DNA foundation models are pretrained by masking parts of a sequence and asking the model to reconstruct them. Standard masked pretraining exposes

arXiv:2609.36222v1 Announce Type: new Abstract: Large language models are increasingly expensive to serve. In large-scale serving systems, autoregressive decoding is often bottlenecked by transferring