Knowledge catalogue
arXiv:2608.28916v1 Announce Type: new Abstract: Automatic speech recognition (ASR) systems are commonly evaluated with word error rate (WER), yet many voice workflows depend on exact written values fo
arXiv:2608.31059v1 Announce Type: cross Abstract: When do text embeddings work as inputs to empirical analysis? Their use rests on an assumption: that we can trade text for its low-dimensional embeddi
arXiv:2608.30725v1 Announce Type: new Abstract: Recent multilingual vision--language encoders cover hundreds of languages in a single model, yet on two state-of-the-art instances retrieval on low-reso
arXiv:2608.29834v1 Announce Type: new Abstract: Collaborative conversations frequently contain references whose targets are indirect rather than named: resolving 'this looks like the fix discussed yes
arXiv:2601.07576v2 Announce Type: replace-cross Abstract: Oral presentation skills are a critical component of higher education, yet comprehensive datasets capturing real-world student performance acr
arXiv:2608.27997v1 Announce Type: new Abstract: Air-ground cross-view referring person detection is a necessary component in the language-to-perception-to-control chain of collective embodied intellig
arXiv:2608.27910v1 Announce Type: cross Abstract: As large language models and increasingly capable AI agents are deployed in high-risk settings, aligning them with complex human values has become a c
Amazon is shutting down Mechanical Turk in September. In 2023, a study from academic researchers in Switzerland found that up to 46% of AMT workers were using AI to complete their tasks. I can’t imagi
arXiv:2607.09893v2 Announce Type: replace-cross Abstract: Sampling from discrete Markov random fields (MRFs) is a hard problem. We study amplitude-encoded i.i.d. sampling for small MRFs where 2^n targ
ggml: add SWIGLU_CLAMP (#27930) ggml: add SWIGLU_CLAMP add vulkan shader Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/44034152 macOS/iOS: macOS Apple Sil
kv-cells: stop the sequence scan once all sequences are seen (#28011) for_each_token_in tested all LLAMA_MAX_SEQ sequences for every used cell, while a cell almost always belongs to one. The scan now
ggml : fix ggml_backend_buft_get_alloc_size() guard (#28038) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/44038725 macOS/iOS: macOS Apple Silicon (arm64)
rpc: avoid serializing buffers from other servers (#26500) rpc: avoid serializing buffers from other servers Only include remote buffer pointers when the buffer belongs to the RPC dispatcher receiving
metal : add remaining Q4_1/Q5_0/Q5_1 fa-vec tunings for M2 (#28017) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/44044108 macOS/iOS: macOS Apple Silicon
hexagon: fix CPY fence bug (#28033) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/44046740 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm
vulkan: top_k radix select for k >= 1024 for Qwen 3.8 Flash Next (#28032) vulkan: add top-k radix sort shader for k >= 1024 add Qwen 3.8 Flash Next top-k tests add top-k qsa fusion clean up code Websi
ggml : add MUL_MAT to the list of ops that may need additional memory (for WebGPU) (#28071) Co-authored-by: Stanisław Szymczyk sszymczy@gmail.com Website: https://llama.app Attestations: https://githu
vulkan: tune mat-vec rows for batched inference on Strix Halo (#27909) vulkan: RDNA3 static mat-vec rows above four columns On RDNA3 above four columns a static 4 rows for all types benches faster tha
spec : fuse the DFlash encoder into the KV cache injection (#27310) dflash : fuse the encoder into the KV injection decode The encoder is a single fc + norm, but running it as a separate llama_encode
sycl : Enhance to get the free memory of Intel GPU (#27968) enhance get mem info by l0 an SYCL API remove debug code, format the code update SYCL.md for GGML_SYCL_GET_MEM_API Website: https://llama.ap
CUDA: extend MOE fusion to specdec, earlier MOE glu fusion and topk-router fusion were restricted to 1 token (#27621) CUDA: extend MOE fusion to specdec, earlier MOE glu fusion and topk-router fusion
metal : add fa-vec tunings for M1 (#28078) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/44172949 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silic
ROCm: add radix TOP_K for long rows (#27466) ROCm: add radix TOP_K for long rows Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/44178618 macOS/iOS: macOS A
webgpu : avoid crash when offset is not multiple of 4 in WebGPU ggml_backend_tensor_get() implementation (#28045) webgpu : avoid crash when offset is not multiple of 4 in WebGPU ggml_backend_tensor_ge
opencl: tune the quant paths for Intel Xe-LP GPUs to improve its TG and PP performance (#26438) opencl: Q4_K/Q5_K mul_mv N_DST 4->8 on Intel for 2x activation reuse opencl: Q4_K mul_mm 8x8 tile fot In
kv-cache : optimize restoring non-contiguous cells (#27991) kv cache : batch state restore scatter reads per contiguous run When restoring state into non-contiguous destination cells (e.g. a prompt-ca
metal : add concat support for quantized types (#28116) Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-0731 Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/442
CUDA: XOR swizzle flash attn K,V smem fp16 tiles (#25635) CUDA: XOR swizzle flash attn K,V smem fp16 tiles Signed-off-by: ynankani ynankani@nvidia.com Fix use 64bit generic pointer instead of 32bit sh
metal : add fa-vec tunings for M1 Ultra (#28088) metal : add fa-vec tunings for M1 Ultra metal : move M1 Ultra tunings after M1 Max section metal : remove duplicate blank line Website: https://llama.a
arXiv:2608.28329v1 Announce Type: new Abstract: Medical question answering (QA) systems have become crucial tools for providing reliable health information. But they remain very unexplored for low-res
arXiv:2608.28188v1 Announce Type: new Abstract: Circuit Representation Learning (CRL) offers a powerful paradigm to guide and optimize core Electronic Design Automation (EDA) tasks, but its practical
arXiv:2602.01335v2 Announce Type: replace Abstract: A visual metaphor constitutes a high-order form of human creativity, employing cross-domain semantic fusion to transform abstract concepts into impa
arXiv:2608.27497v1 Announce Type: new Abstract: Recent embodied models increasingly leverage geometric representations to improve spatial reasoning and robotic manipulation. However, existing reconstr
arXiv:2608.27757v1 Announce Type: new Abstract: Searchless chess networks reach human master strength from a single forward pass by imitating a stronger teacher: the strongest, Leela Chess Zero's (Lc0
arXiv:2608.27785v1 Announce Type: new Abstract: We study audio-visual conflict as a compositional generalization test for AV-LLMs: the model must combine synchronized but semantically incompatible aud
arXiv:2502.15438v5 Announce Type: replace Abstract: Vision-based occupancy networks (VONs) provide an end-to-end solution for reconstructing 3D environments in autonomous driving. However, existing me
arXiv:2608.27728v1 Announce Type: new Abstract: Diffusion models generate skillful weather ensembles but require costly iterative sampling. We introduce a supervised energy-distance distillation metho
arXiv:2608.28046v1 Announce Type: cross Abstract: Collective behaviour in living systems is usually modelled as the outcome of a direct social drive: agents are rewarded, or hard-wired, to align with
arXiv:2509.20191v2 Announce Type: replace-cross Abstract: Approximating solutions to partial differential equations (PDEs) is fundamental for the modeling of dynamical systems in science and engineeri
arXiv:2608.28386v1 Announce Type: new Abstract: Existing monocular full-body 3D human-object interaction (HOI) methods do not combine explicit finger-level grasp optimization with category-agnostic ob
Great paper from Google and colleagues. It proposes an interesting approach to improve agents on long-horizon tasks. Long-running agents slow down and start poisoning their own context. Both symptoms
Grok @Bot only gets better from here Gavin Baker says Grok Bot feels like another ChatGPT moment because it turns hours of Claude Code work into seconds: 'You see these 23-year-old kids and just the w
How fast is the Claude Code plugin ecosystem actually growing? Plugin-touching commit activity grew 8.8x in the six months after the initial launch. Researchers studied 1,926 repositories hosting plug
arXiv:2608.28482v1 Announce Type: new Abstract: This paper evaluates how reward function choice shapes the performance and behavior of LLM forecasters. We compare five proper scoring rules as training
arXiv:2608.28517v1 Announce Type: new Abstract: Cross-modal image translation in remote sensing must preserve source-observed content while matching the target-domain distribution. Existing methods jo
The LWiAI Podcast #255 (August 26 2026) reviewed recent AI alerts, including Google’s Gemini 3.7 Flash, Jalapeño’s record‑speed benchmark results, Qwen 3.8, and a case of an entirely AI‑guided drone t
arXiv:2511.07011v2 Announce Type: replace Abstract: Background: Remotely captured spoken language could provide objective, regular indicators of depression symptom severity. However, research to date
When using kvarn quants at low context depth tg speed is similar to llama.cpp on and equivalent qx_x quant. However, as context depth grows kvarn tanks your tg speed. This fork optimises kvarn to have
Oh fuck. Agents like Claude, Codex and Hermes are installing unowned code in corporate networks. As if we didn’t have enough to worry about. H/t @HeidyKhlaaf. (See also my Substack w @nathanhamiel “LL
arXiv:2608.28213v1 Announce Type: new Abstract: People read a humanoid robot's motion in social settings not only for the action performed but for the affect conveyed. Motion carrying that affect has
arXiv:2608.27923v1 Announce Type: new Abstract: Printed circuit boards (PCBs) are fundamental to modern electronic systems, yet AI-driven PCB design automation remains constrained by the lack of large
People don't understand. You can create a rl env to teach it to find quarters. This will make money while you sleep. Media I DON’T THINK PEOPLE REALIZE HOW MASSIVE THIS IS YET @HuggingFace and @Pollen
potentially MUCH more serious than the OpenAI Hugging Face incident — but lacks the vivid “civilizational” drama. so few people are paying attention. Oh fuck. Agents like Claude, Codex and Hermes are
arXiv:2608.28453v1 Announce Type: new Abstract: Accurate segmentation of interstitial lung disease (ILD) patterns is essential for quantitative disease assessment and longitudinal monitoring. However,
arXiv:2608.27626v1 Announce Type: cross Abstract: Quantum DeepONet accelerates neural-operator inference by evaluating an orthogonally parameterized network on a quantum computer, reproducing in ideal
arXiv:2608.28219v1 Announce Type: new Abstract: Cross-identity character animation aims to drive a target identity from a reference image to follow the motion of a source character from a driving vide
arXiv:2608.27877v1 Announce Type: new Abstract: Linking the internal representations of deep neural networks (DNNs) to human mental representations is important for using DNNs as computational models
TL;DR - yeah it works, no wild skills or patching required. 37-50 tg/s when generating text, spiking over 60tg/s when writing code and mtp hits hard. Your results can be better if you have a better mo
arXiv:2608.27678v1 Announce Type: new Abstract: Offline goal-conditioned reinforcement learning (GCRL) often uses trajectory structure for future-goal sampling and multi-step targets, yet logged traje
arXiv:2603.21840v2 Announce Type: replace Abstract: Human annotation cost and time remain significant bottlenecks in Natural Language Processing (NLP), with test data annotation being particularly exp