b10303
sycl : fix error Error OP FLASH_ATTN_EXT on arc770 (#26441) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) i
Knowledge catalogue
sycl : fix error Error OP FLASH_ATTN_EXT on arc770 (#26441) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) i
sycl : Support DSv4 OPs: LIGHTNING_INDEXER,DSV4_HC_COMB,DSV4_HC_POST,DSV4_HC_PRE (#26568) support DSv4 OPs: LIGHTNING_INDEXER,DSV4_HC_COMB,DSV4_HC_POST,DSV4_HC_PREwq update ops.md fix format issue Web
sycl: *glu flat path (#26354) tests: add SWIGLU perf cases perf mode had no GLU coverage. Adds SWIGLU at 17408 columns, 512 and 2048 tokens, f16 and f32, with the operands both fused and split. sycl:
sycl: fix UE4M3 parsing (#25608) The NVFP4 quantization format stores a scaling factor for every group of 16 weights, packed into a single UE4M3 byte. The SYCL GPU code was converting these scale valu
Mitigate crashing issue on Windows MSYS2 UCRT64 environment (GCC 16.1.0) (#26555) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABL
ggml : add aarch64 HWCAP fallbacks and fix fp16 variant detection (#25554) ggml : add fallback definitions for missing aarch64 HWCAP bits ggml : require HWCAP_ASIMDHP for the aarch64 fp16 cpu variants
mtmd: stop feeding the text stream again during Qwen3-TTS generation (#26706) The reference implementation has two mutually exclusive prompt layouts. In non streaming mode the prefill carries the whol
server: (router) do not evict busy models (#26567) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFram
server: (router) add LRU scheduler (#26572) add lru_sched handle coalescing (req leaves waiting queue) add tests fix stream case address review comments Website: https://llama.app macOS/iOS: macOS App
sync : ggml Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux: Ubuntu x64 (CPU) Ubuntu ar
mtmd: fix longest_edge ignoring min/max pixels (#26638) mtmd: fix longest_edge ignoring min/max pixels nits Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64
metal : fix NORM/RMS_NORM for row lengths that leave a partial simdgroup (#26708) ggml_metal_op_norm sized the threadgroup with nth = std::min(nth, args.ne00_t), which can leave nth not a multiple of
sycl: coalesce the ssm_conv window loads (#26612) test-backend-ops perf -o SSM_CONV on an Arc Pro B70, interleaved A/B against master, 6 reps, us/run: ne_a=[515,3328,1,1] ne_b=[4,3328,1,1] n_t=512 97.
tts: account for the vocoder pass in the timings line (#26733) get_output runs the waveform work the pipeline defers to it, from a single trailing window to a full pass depending on the model. Measuri
On August 7, 2026 Ethan Mollick tweeted that “every remaining good AI benchmark score has an implied asterisk next to it which reads: * could be significantly higher with a better harness.” The commen
arXiv:2608.06312v1 Announce Type: new Abstract: Large language models (LLMs) increasingly support complex professional tasks, yet their capabilities in rule-intensive document review remain insufficie
arXiv:2608.06329v1 Announce Type: cross Abstract: Task-oriented conversational agents are evaluated using curated or automatically generated benchmarks, yet benchmark quality is rarely assessed. Poor
arXiv:2608.05250v1 Announce Type: new Abstract: Multi-task supervised fine-tuning (SFT) often casts a heterogeneous data mixture as a single optimization problem, even though different tasks may reach
arXiv:2608.05253v1 Announce Type: new Abstract: Quantized orthogonal fine-tuning (qoft) enables parameter-efficient adaptation of low-bit language models by learning structured activation rotations be
arXiv:2608.06111v1 Announce Type: cross Abstract: Positional embeddings (PE) in Transformers encode token distance and order but are largely agnostic to extit{syntactic structure}. We introduce extbf{
arXiv:2608.05960v1 Announce Type: cross Abstract: Routine CT interpretation is inherently comprehensive, capturing incidental findings across the entire scan volume. 3D CT foundation models could assi
arXiv:2608.05381v1 Announce Type: new Abstract: Current Multimodal Large Language Models (MLLMs) can process diverse sensory inputs, yet their reasoning remains heavily biased toward a dominant modali
arXiv:2608.05420v1 Announce Type: cross Abstract: Large language models (LLMs) can generate text that resembles a mathematical proof, but resemblance does not establish correctness. A formal proof che
today was the last day of my subscription on ollama cloud, to be honest it was a great price value for me and with GLM 5.2 and Deepseek V4 Pro i was able to Vibe code my custom woocomerce shop with mu
arXiv:2608.05359v1 Announce Type: new Abstract: CASCADE is an agentic framework that predicts downstream transcriptional effects of gene perturbation from precomputed ARACNe regulatory networks, expos
arXiv:2608.05906v1 Announce Type: new Abstract: LLM agents that repair failures often discard successful corrections, forcing later episodes to rediscover similar solutions. We study whether finalized
arXiv:2608.05790v1 Announce Type: new Abstract: General-purpose large language model agents have achieved strong performance on tool-augmented tasks, yet they rely on assumptions break down in blockch
arXiv:2608.05631v1 Announce Type: new Abstract: Multimodal large language models excel at passive perception but struggle with complex visual cognitive tasks requiring multi-step temporal reasoning. T
arXiv:2608.05195v1 Announce Type: cross Abstract: A natural language interface can be used to make cancer genomics databases easier to use, but even if a question is perfectly fluent, its scientific m
arXiv:2603.14158v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are entering clinical workflows, yet evaluations rarely assess how clinician reasoning shapes model behavior duri
arXiv:2608.05167v1 Announce Type: new Abstract: Token-based encoders like BERT treat Chinese characters as atomic identifiers, ignoring their recursive orthographic structure. Consequently, models rel
arXiv:2608.05886v1 Announce Type: cross Abstract: Modern LLM coding agents such as Claude Code and OpenHands share a common inefficiency: they spend much of their token budget finding the file to patc
Codex is overoptimised for large models: it ranks 2nd out of 10 for GLM 5.2 but drops to 9th place for Gemma-4! Almost all the effort in this field goes into tuning the weights. We wanted to know how
arXiv:2608.05166v1 Announce Type: new Abstract: We present an evaluation of cognitive bias expression in state-of-the-art instruction-tuned LLMs under realistic multi-turn interaction settings. Our wo
arXiv:2608.06216v1 Announce Type: cross Abstract: Classical continual learning (CL) has primarily focused on enabling models to update and retain knowledge through parameter-centric mechanisms, e.g.,
arXiv:2608.05169v1 Announce Type: new Abstract: Long-form story generation requires models to preserve narrative consistency across extended contexts, yet existing prompting-based methods often accumu
arXiv:2604.03750v2 Announce Type: replace-cross Abstract: Reverse engineering (RE) is central to software security, particularly for cryptographic programs that handle sensitive data and are highly pr
arXiv:2508.02091v4 Announce Type: replace-cross Abstract: Approximate nearest-neighbor search (ANNS) algorithms have become increasingly critical for recent AI applications, particularly in retrieval-
arXiv:2608.05164v1 Announce Type: new Abstract: Independently trained large language models may develop shared internal representations of semantic concepts despite architectural differences -- but wh
arXiv:2608.05877v1 Announce Type: cross Abstract: Optimal transport (OT) has emerged as an effective framework for unsupervised action segmentation. Yet, in existing OT-based methods, the latent actio
arXiv:2608.00641v2 Announce Type: replace Abstract: Bayesian optimization (BO) relies on a surrogate model and an acquisition function, yet the most suitable choices vary across tasks and optimization
arXiv:2608.06243v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) improves the reasoning capabilities of large language models using automatically verifiable outcom
arXiv:2608.05238v1 Announce Type: new Abstract: Training multimodal models to align time series with language runs into a self-supervision trap. The usual recipe asks an LLM to read a series and write
arXiv:2608.05930v1 Announce Type: cross Abstract: The experience sampling method (ESM) is a longitudinal research design where participants report their thoughts, emotional states and behaviours multi
DeepSeek-V4-Flash-0731 is now fully rolled out as the new default for deepseek-v4-flash on Ollama's cloud. This model combines speed, efficiency, and frontier-level performance. Fast: 120+ output tps
arXiv:2608.06075v1 Announce Type: cross Abstract: Commercial vision-language models are reshaping computer vision, with visual priors broad enough to rival task-specific systems. This raises a natural
arXiv:2608.05170v1 Announce Type: cross Abstract: Role-playing agents (RPAs) have emerged as a key application of large language models, enabling immersive and high-fidelity character simulation. Accu
arXiv:2603.00393v2 Announce Type: replace-cross Abstract: Inverse problems constrained by partial differential equations are often ill-conditioned due to noisy, incomplete data or inherent non-uniquen
arXiv:2608.06031v1 Announce Type: new Abstract: Dynamic graph prompting freezes a pre-trained temporal backbone and adapts it to label-scarce downstream tasks using lightweight prompts. However, exist
arXiv:2608.05505v1 Announce Type: new Abstract: Acting in a physical scene requires knowing its real later state, not a plausible one. Current evaluations often accept words or a realistic-looking ima
arXiv:2608.06110v1 Announce Type: new Abstract: This paper presents ECHO (Enhanced Care & Health Observer), a locally-deployable conversational health assistant for long-term chronic care management.
Code and instructions available here: https://github.com/albertoZurini/echo-dot-2-playground Hello there! After a few days of experimenting I was able to get a completely local voice pipeline running
arXiv:2608.05519v1 Announce Type: new Abstract: Agent benchmarks usually measure task completion and treat resource use as an auxiliary statistic. In deployment, however, the choice among a local look
arXiv:2608.05464v1 Announce Type: cross Abstract: The pruning of network connections is key to brain function but, despite its importance, there exist few biologically-plausible pruning rules with dem
arXiv:2608.05811v1 Announce Type: new Abstract: Pixel-space generative models bypass lossy latent compression, yet necessitate joint learning of global structure and fine-grained details in a high-dim
arXiv:2608.05605v1 Announce Type: cross Abstract: Research and Education Networks (RENs) serve as critical infrastructure for scientific discovery, yet they face a unique security paradox: their norma
arXiv:2608.05832v1 Announce Type: new Abstract: Large language models (LLMs) excel in structured tasks but struggle with dynamic social interactions, where success requires long-term goal coordination
arXiv:2608.06022v1 Announce Type: new Abstract: Epitopes determine where antibodies bind antigens and shape downstream therapeutic properties such as functional blockade and escape resistance, making
arXiv:2608.05522v1 Announce Type: cross Abstract: Estimating positive largest Lyapunov exponents from data is comparatively natural because neighboring trajectories separate, whereas stable dynamics r
Hey peeps. I know you're tired of low quants giving hard to believe numbers. I'm quite skeptical too and from what I tried I'm often left with the impression that the claims fall short. So this model