Knowledge catalogue
arXiv:2610.08828v1 Announce Type: new Abstract: Small-data adaptation can improve speech detection while degrading speaker attribution. We study this discrepancy in a released streaming diarizer adapt
arXiv:2610.10335v1 Announce Type: new Abstract: Visual in-context learning (ICL), well suited to label-scarce medical imaging, uses support image-label pairs to demonstrate input-output mappings, whil
arXiv:2610.09607v1 Announce Type: new Abstract: Skeleton-based reasoning prompting is a promising training-free approach for structuring LLM reasoning, but prior work largely assumes an English-centri
whoops I hit send and went to a meeting, didn't realize the repo wasnt public- it is now! it's a chrome extension I use every day now https://github.com/ThariqS/ai-newtab you now get Claude API credit
arXiv:2610.09134v1 Announce Type: new Abstract: Robot world models support policy evaluation, planning, and synthetic data generation, but these applications require predictions that distinguish succe
you now get Claude API credits with your MAX plans ($100, or 200 matching your plan) every month, use this to build more personal AI for yourself! I made an AI homepage that's generated everyday based
arXiv:2501.07972v2 Announce Type: replace-cross Abstract: The target of video moment retrieval (VMR) is predicting temporal spans within a video that semantically match a given linguistic query. Exist
arXiv:2610.07423v1 Announce Type: new Abstract: Field-effect transistor (FET) layouts on exfoliated two-dimensional flakes are typically drawn by hand for each flake, placing contacts and gates to mat
I've been tinkering with GLM-5.3-Flash on two 64GB CMP 170HX cards for a while, and the setup is finally stable enough that I figured I'd share it. I also compared it against the Qwen3.8-Flash-Next se
arXiv:2607.10826v2 Announce Type: replace-cross Abstract: Automated evaluation is essential for scaling generative 3D systems, where exhaustive human review is costly and slow. Yet the reliability of
A 200 AI subscription can be worth 12,000 in tokens. Which plan delivers it is not close. 'They're selling to willing buyers at the fair market price. This is capitalism.' 'You can pay 200 for a Claud
arXiv:2610.07626v1 Announce Type: cross Abstract: Prosodic stress is a crucial aspect of automatic pronunciation assessment (APA), encompassing both sentence stress detection (SSD) and word stress det
arXiv:2610.07391v1 Announce Type: cross Abstract: We present a new perspective on the problem of likelihood approximation within the framework of simulation-based inference that promotes scalable and
arXiv:2610.08049v1 Announce Type: new Abstract: Low-rank adaptation (LoRA) is widely used as a parameter-efficient fine-tuning technique for pre-trained deep neural networks, which approximates the we
arXiv:2610.08365v1 Announce Type: new Abstract: We adapt Stevens's power law to measure the innate ability of AI models to read visualizations, which can reveal the built-in perceptual mechanisms of a
Yesterday TechCrunch published a piece about a growing problem for AI agents: websites are starting to block them. Amazon blocking Meta's Muse is the obvious example. At almost exactly the same time,
arXiv:2610.07544v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to judge how well an advertisement matches a query, but the fairness of these judgments has received
arXiv:2610.08680v1 Announce Type: cross Abstract: Endpoint accuracy on abstract-reasoning benchmarks does not reveal whether a language model has acquired a transferable rule or fit distribution-speci
arXiv:2610.07274v1 Announce Type: new Abstract: Deterministic benchmark scores show that an agent received credit, but not whether that credit was earned, reported honestly, or would hold on a second
arXiv:2610.07356v1 Announce Type: cross Abstract: Systems engineers use several diagrams to describe the structure and behavior of systems. Engineers create these diagrams together to make sure that t
arXiv:2610.08444v1 Announce Type: new Abstract: Vision-language-action (VLA) policies repeatedly invoke inference to control robots, making graphics processing unit (GPU) energy a recurring cost of ta
arXiv:2610.07475v1 Announce Type: new Abstract: Adapting a reinforcement learning policy to changes in another agent's behavior typically requires a large amount of new interaction data. Policy sensit
arXiv:2610.08775v1 Announce Type: new Abstract: Large language models (LLMs) can solve many narrow tasks, but querying them separately for millions of related instances can be prohibitively expensive.
Agent-to-agent communication with a personal agent on top is wild. Wow. I underestimated how well models like Opus 5.5 can coordinate already. This opens a whole new set of experiences with agents. Bu
arXiv:2610.04188v2 Announce Type: replace Abstract: Recent studies show that artificial intelligence (AI) with language and vision capabilities still experiences limitations in spatial reasoning. In t
arXiv:2610.07707v1 Announce Type: new Abstract: Conversational AI assistants with long-term memory extract facts from user messages into a store consulted in later conversations. A stated plan can ent
arXiv:2610.08779v1 Announce Type: new Abstract: Current video editors can insert objects but often struggle to make them participate in interactions such as being picked up or manipulated. We introduc
arXiv:2610.07819v1 Announce Type: cross Abstract: Model merging offers a promising solution for combining multiple fine-tuned checkpoints into a single model through parameter arithmetic. However, fin
arXiv:2610.07029v1 Announce Type: cross Abstract: Resistive random-access memory (ReRAM)-based Processing-in-Memory (PIM) accelerator is a promising platform for processing massively memory intensive
arXiv:2610.06988v1 Announce Type: new Abstract: Knowledge tracing (KT) models are predominantly evaluated using aggregate metrics such as area under the curve (AUC) and accuracy. However, these global
arXiv:2610.07694v1 Announce Type: new Abstract: The integrative analysis of histopathological Whole-Slide Images (WSIs) and transcriptomic profiles holds significant promise for cancer survival predic
Another PR of ours just merged into llama.cpp: the fast Metal kernels from Monday now cover all 26 weight formats the Mac GPU runs. They made speculative decoding faster on Mac for 10 formats, and thi
Carl Franzen / VentureBeat: Anthropic cuts Sonnet 5.5 cache read price from 0.20 to 0.10 and adds monthly API credits: 100 for Max 5x, 200 for Max 20x, up to 500 shared by Team users — The model start
Anthropic: Anthropic launches Claude Haiku 5.5, the first Haiku model with effort controls, for high-volume, cost-sensitive tasks like summary and classification requests — Introducing Claude Haiku 5.
Frederic Lardinois / The New Stack: Anthropic prices Haiku 5.5 at 0.10/1M input and 0.50/1M output tokens for requests up to 100K tokens, and 0.50 and 2.50 above, vs. 1 and 5 for Haiku 4.5 — Anthropic
Anthropic PBC today released Claude Haiku 5.5, pricing its newest small model at roughly a quarter of what Haiku 4.5 costs to run. Claude Sonnet 5.5 is getting cheaper as well, since the company is ha
arXiv:2610.06966v1 Announce Type: cross Abstract: Indirect prompt injection (IPI) hides adversarial instructions in content that large language model (LLM) agents read at runtime. As agents compose he
arXiv:2610.07438v1 Announce Type: cross Abstract: Artifact removal routinely precedes the classification of electrodermal activity (EDA), on the assumption that a cleaner signal supports a better deci
arXiv:2610.07292v1 Announce Type: cross Abstract: Missing covariates are frequently encountered in supervised learning problems, and classical methods for estimation using such data use carefully chos
arXiv:2610.07637v1 Announce Type: cross Abstract: Many real-world datasets exhibit unusually large values far more frequently than predicted by Gaussian models. Heavy-tailed distributions capture this
arXiv:2610.06927v1 Announce Type: cross Abstract: The key-value (KV) cache of autoregressive transformers grows linearly with context length and dominates memory at long context. Most training-free re
arXiv:2601.17645v2 Announce Type: replace-cross Abstract: Internet audio-visual clips convey meaning through time-varying sound and motion, which extend beyond what text alone can represent. To examin
arXiv:2610.06892v1 Announce Type: cross Abstract: Learning from human preference data is the dominant route to aligning language models with human values. In linear social choice, where rewards are li
ggml-webgpu: no dawn native features on wasi (#27069) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/53445261 macOS/iOS: macOS Apple Silicon (arm64) macOS
sycl: add IQ3_S multi-column MMVQ (#29500) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/53455527 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silic
vulkan: fix amd iGPU slow checkpoint read (#30049) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/53465294 macOS/iOS: macOS Apple Silicon (arm64) macOS App
ggml-webgpu: fix flash_attn supports_op check for overlapping KV (#28205) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/53548008 macOS/iOS: macOS Apple Si
imatrix : include clocale for std::setlocale (#30079) Co-authored-by: yarik dazzywi@github.com Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/53551657 macO
vendor : update cpp-httplib to 0.60.0 (#30081) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/53557265 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple S
musa: use the tile lightning indexer kernel (#30080) Signed-off-by: Xiaodong Ye xiaodong.ye@mthreads.com Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/535
vocab : add plamo fim tokens (#30090) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/53567889 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (a
sampling : use greedy selection for eligible temperature-zero chains (#29797) sampling : use greedy selection for eligible temperature-zero chains Assisted-by: OpenAI Codex Apply suggestion from @gger
feat: add GLM5Next MTP, optimize (#29928) llama : add GLM5-Next NextN (MTP) graph Build the GLM5-Next multi-token-prediction head as graph_mtp: the NextN block embeds enorm(tok)+hnorm(h) through eh_pr
metal : fix MUL_MAT+ADD fusion when the residual is itself a MUL_MAT (#30100) metal : fix MUL_MAT+ADD fusion when the residual is itself a MUL_MAT ggml_metal_op_mul_mat_mma picks the residual of a fus
metal : few-row MMA mat-mul for the remaining src0 types (#30065) The generic few-row MMA kernel works for any type with a 16-weight dequantizer, so it now also takes BF16, Q1_0, Q2_0, MXFP4, Q2_K, Q3
llama: share the nextn tensor flags between models Follow-up of the TODO in glm5-next: move the trunk-only and MTP-only detection that each model copied into a nextn_flags helper of llama_model_base.
Banger paper from NVIDIA. One exciting trend I am seeing is building verifiable environments for your agents and training the harness alongside the model. Co-evolving the harness and the model is a bi
arXiv:2610.07417v1 Announce Type: cross Abstract: Bayesian Optimization (BO) has become an established methodology for minimizing black-box functions of a vector input. Often, however, this parameter
arXiv:2610.07056v1 Announce Type: cross Abstract: Behavioral cloning (BC), despite its simplicity, exhibits many counterintuitive phenomena in the real world. For example, the performance of BC often
arXiv:2610.07674v1 Announce Type: cross Abstract: Controlling a hybrid system to a target set under parameter uncertainty can require informative actions that temporarily drive the system state away f