Knowledge catalogue
arXiv:2609.29618v1 Announce Type: cross Abstract: We report an exploratory, single-seed ablation of TALH (Adaptive Latent Hybrid), a decoder-only language model with parallel Multi-head Latent Attenti
arXiv:2609.28528v1 Announce Type: cross Abstract: The goal of this note is to give a detailed proof, to the best of our understanding, of the recent presentation by Harrison and Leeman (arXiv:2609.176
arXiv:2609.28551v1 Announce Type: cross Abstract: When can a learner make only finitely many prediction errors along every infinite sequence labeled by a fixed, unknown hypothesis? We characterize thi
arXiv:2609.29825v1 Announce Type: new Abstract: Patient-specific 4D myocardial reconstruction from cine MRI supports quantitative functional assessment, regional motion analysis, and simulation-based
arXiv:2609.29766v1 Announce Type: cross Abstract: Cross-speaker acoustic-to-articulatory inversion requires accounting for anatomical differences between speakers. We propose a geometric adaptation fr
arXiv:2609.30212v1 Announce Type: cross Abstract: We study the deterministic oracle complexity of finding approximate solutions to composite monotone inclusion problems, formed by the sum of a smooth
another stealth model launch Space Bunny Alpha is now FREE on Nous Portal try with your Hermes Agent now Meet Space Bunny Alpha on OpenRouter ⚡ A flash model with fast inference, adjustable reasoning,
arXiv:2609.29176v1 Announce Type: new Abstract: The human wrist exhibits adaptive stiffness modulability: joint stiffness anisotropy can be actively regulated through muscle co-contraction. This funct
arXiv:2609.28973v1 Announce Type: new Abstract: Physical changes or sensing errors can invalidate embodied agents' task-relevant beliefs. AquaMend compares re-probing, rollback, and supported continua
arXiv:2609.29349v1 Announce Type: cross Abstract: ArGuard is a shared task on harmful content detection in Arabic memes and LLM prompts. It includes two tracks: Track A focuses on multimodal hate dete
arXiv:2609.30184v1 Announce Type: new Abstract: U.S. employment-discrimination complaints describe complex event sequences that are not explicitly captured by lexical or embedding-based representation
arXiv:2609.30030v1 Announce Type: new Abstract: A synthetic survey can reproduce the average answer while misrepresenting how people differ, how their answers relate to one another, or how they respon
arXiv:2609.29191v1 Announce Type: new Abstract: Sensitive information is defined by domain and intent, not a universal category, yet redaction systems such as privacy filters and named-entity recogniz
arXiv:2609.29198v1 Announce Type: new Abstract: Accurate digital maps are essential for Advanced Driver Assistance Systems (ADAS) or Autonomous Driving (AD), providing critical information such as roa
arXiv:2609.30088v1 Announce Type: cross Abstract: Graph-structured optimization with linear constraints is fundamental to critical infrastructure but faces scalability limits due to massive strict har
arXiv:2609.28581v1 Announce Type: cross Abstract: Reinforcement-learning (RL) policies are often distributed as opaque neural checkpoints, while training logs show that a run occurred without explaini
arXiv:2609.29952v1 Announce Type: new Abstract: Before a product or policy change ships, the question that matters is how people will react to it. Augur rehearses that reaction offline: it builds a ty
Automated AI theorem proving has moved the frontier: The holy grail is not an AI that can produce an endless pile of true theorems. It’s an AI that can discover mathematics, and build each discovery i
arXiv:2609.30009v1 Announce Type: cross Abstract: Financial institutions operate under dense, frequently amended rulebooks, and answering a compliance question correctly requires not only fluency but
arXiv:2609.28908v1 Announce Type: cross Abstract: Agent behavior depends on the harness surrounding a language model, but it remains unclear whether language models can reliably improve such harnesses
arXiv:2609.28998v1 Announce Type: new Abstract: Low-rank adaptation (LoRA) has become a popular parameter-efficient fine-tuning method for large language models. A key challenge in LoRA is how to dete
arXiv:2609.29816v1 Announce Type: new Abstract: Recent years have witnessed major progress in joint audio-video generation. Existing models still suffer from limited per-modality fidelity, insufficien
metal : fix graph capture and handle empty graphs (#29390) return early when the graph has no nodes drop the redundant reset of capture_compute: the decrement at the top of the function already transi
hexagon: use DMA for contiguous dim1 CONCAT (#29404) hexagon: use DMA for contiguous dim1 CONCAT Assisted-by: OpenCode hexagon: update CONCAT DMA for DMA64 Assisted-by: OpenCode Website: https://llama
hexagon: add q5_k quant type support (#29123) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/50064037 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Si
CUDA: fuse RMS_NORM + SCALE into one kernel (#29393) #28068 builds the GDN q/k l2norm as ggml_scale(ggml_rms_norm(x, eps/n), 1/sqrt(n)). This adds 2 SCALE nodes per GDN layer, 96 extra kernel launches
musa: fix PH1 (MTT S5000) operator failures and build issues (#29193) musa: use 16-byte copies for MUSA like sm_70+ ggml_cuda_get_max_cpy_bytes() derives the copy width from CUDA_ARCH. mcc never defin
[SYCL] support sparse FA (#28796) fix conflict fix format issue rm unused code Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/50188435 macOS/iOS: macOS App
rpc: include nb in the get_alloc_size cache key and floor the result at ggml_nbytes (#29283) rpc : include nb in the get_alloc_size cache key and floor the result at ggml_nbytes cont : remove redundan
HIP: bump HIP_VERSION requried for fp8 to avoid missing __hip_fp8_e4m3 support in 6.2 (#29231) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/50216799 macO
llama : add llama_prec_policy + model-driven W4A4 path (#24364) Rebase and update based on #26675 Signed-off-by: ynankani ynankani@nvidia.com CI failure fix(launh_bounds overload on HIP) and cleanup S
metal : split fa kernels into per-dtype libraries (#29329) metal : split fa kernels into per-dtype libraries Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp cont : minor fix comment Website: ht
metal: FWHT kernels for block widths above 512 (#29095) metal: FWHT kernels for block widths above 512 The Metal FWHT covers widths 64 to 512, one row per simdgroup with N/32 values per lane. Wider bl
common : extract shared unicode path/string helpers (#29415) Signed-off-by: Adrien Gallouët angt@huggingface.co Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestati
Fixing the vulkan build issue of legacy GLSLC version that has no cooperativeMatrix API support (#29373) (#29409) vulkan : fix build issue of legacy glslc version by adding GGML_VULKAN_COOPMAT_GLSLC_S
opencl: add bin kernel kernel_gemm_noshuffle_q5_k_f32_32b_trans_ila_a8_bin, kernel_gemm_noshuffle_q5_k_q8_1_dp4a_ila_a8_bin (#29401) opencl: add A8 Q5_K non-MoE non dp4a + dp4a binary kernel opencl: f
mtmd: fix mel preprocessor in LFM2 audio (#29403) which resulted in different greedy transcripts for 4.5% of English and 6.5% of Japanese test utterances. In Japanese, some differences changed entire
common,rpc : simplify fs_create_directory_with_parents() (#29432) The original function was broken on Windows for some unicode paths Paths without a trailing separator now create the last directory to
arXiv:2609.28963v1 Announce Type: new Abstract: Group-based reinforcement learning (RL) methods, such as GRPO and its variants, have become a leading paradigm for training reasoning and agentic large
arXiv:2404.06022v3 Announce Type: replace-cross Abstract: Face forgery detection faces critical challenges in generalizing to unseen manipulation techniques and remaining robust under image compressio
arXiv:2609.29694v1 Announce Type: new Abstract: We study realizable multiclass PAC learning with bandit feedback: the learner observes an i.i.d. instance, predicts one of K labels, and learns only whe
Banger paper from Microsoft and colleagues. We talk about human taste being important in this AI era. But for recursive self-improvement, an agent's taste also matters. The big question is: How often
Banger paper from Microsoft on prompt optimization. (bookmark it) The claim that a coding agent reading your logs beats GEPA at prompt optimization The overall finding is that you want to give a codin
Banger report on building faster memory for AI Agents. If your agent's memory layer is slow, this design is worth a look. Great weekend read. It proposes a new agentic memory architecture, Jev-Mem, in
arXiv:2609.29146v1 Announce Type: new Abstract: Bangla, the seventh most spoken language in the world, remains under-resourced for neural text-to-speech. Public Bangla speech corpora are dominated by
arXiv:2609.29371v1 Announce Type: new Abstract: This paper presents BanglaTurn, a corpus for end-of-turn detection in Bangla conversational speech, and a model trained on it. The corpus holds 35,374 s
arXiv:2609.28557v1 Announce Type: new Abstract: DNA sequencing pipelines, spanning quality control, alignment, variant calling, and annotation, are now reliably executed by workflow management systems
arXiv:2609.29397v1 Announce Type: new Abstract: Ternary (1.58-bit) weights are attractive for microcontroller-class language models, but the sub-1M-parameter regime rests mainly on isolated, single-se
arXiv:2609.29266v1 Announce Type: new Abstract: We develop a multi-label Polish content-safety classifier by fine-tuning allegro/herbert-base-cased (124M) across five categories (hate, vulgarity, sexu
arXiv:2609.29798v1 Announce Type: cross Abstract: This paper presents an end-to-end study of automatic speech recognition (ASR) for adolescent health communication in three Ghanaian languages (Twi, Da
arXiv:2609.29559v1 Announce Type: new Abstract: Arabic-Russian machine translation (MT) remains under-explored due to the rich morphology of Arabic and low lexical overlap between the two languages. W
arXiv:2609.28673v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed as argumentative agents in persuasive dialogues, necessitating rigorous evaluation of their debat
arXiv:2609.28991v1 Announce Type: cross Abstract: Video understanding is increasingly performed by multi-stage LLM agents that separate temporal grounding, visual observation, and reasoning. Yet these
Reinforcement learning (RL) has been a keystone of modern LLM post-training, but it demands large training clusters and access to model internals that external customers can't have with proprietary mo
arXiv:2609.29744v1 Announce Type: cross Abstract: We present: (i) a new dataset consisting of the full development history of a 21,000-line Python tool built entirely by Claude AI, with no human-autho
arXiv:2609.29960v1 Announce Type: cross Abstract: Fine-tuning large language models on new objectives can improve helpfulness, instruction following, or domain-specific performance, but it can also in
arXiv:2609.30198v1 Announce Type: new Abstract: Latent neural surrogate solvers, or latent dynamics models, accelerate simulations of time-dependent physical systems by evolving a compressed latent sp
arXiv:2609.29307v1 Announce Type: new Abstract: Brain-age prediction from resting-state fMRI provides a quantitative framework for characterizing age-related changes in spontaneous brain dynamics and
arXiv:2609.29866v1 Announce Type: cross Abstract: Deploying real-time speech enhancement on resource-constrained devices requires meeting strict latency, memory, and energy constraints. Microcontrolle
arXiv:2603.11133v2 Announce Type: replace Abstract: Sequence modeling tasks can involve intrinsic higher-order dependencies, while standard self-attention assigns scores to token pairs and does not ex