Auditable Claims about AI Agents
arXiv:2610.07459v1 Announce Type: new Abstract: Organizations make claims about their AI agents: a person approves every external email, every action is logged, an evaluation shows the agent is safe t
Knowledge catalogue
arXiv:2610.07459v1 Announce Type: new Abstract: Organizations make claims about their AI agents: a person approves every external email, every action is logged, an evaluation shows the agent is safe t
arXiv:2610.08119v1 Announce Type: new Abstract: World-action models (WAMs) such as Cosmos 3 jointly generate future video and robot actions from an observation and instruction. Adapting one such model
AWS DevOps Agent can diagnose production incidents but is kept in observe-and-report mode so it does not change resources directly. This post shows how to use AWS Lambda Durable Functions, Amazon Even
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.
arXiv:2610.08772v1 Announce Type: new Abstract: Diffusion Transformers (DiTs) have achieved strong performance in image and video generation, but the quadratic complexity of full attention makes high-
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:2604.01064v2 Announce Type: replace Abstract: Despite advances in reinforcement and imitation learning, achieving both precise control and dynamic whole-body behaviors in long-horizon tasks rema
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
Becoming an AI superuser is NOT about knowing where the buttons are - it's a mindset and behavior shift. And the Mastermind is where we get it done. You've got less than 3 more hours to grab the AI Ag
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:2610.08450v1 Announce Type: new Abstract: Autonomous vehicles (AVs) have significantly advanced in real-world deployment in recent years, yet safety continues to be a critical barrier to widespr
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
arXiv:2610.07420v1 Announce Type: new Abstract: Electroencephalography (EEG) signals drift over time, which can cause static brain-computer interface (BCI) models to degrade in practice. We present a
arXiv:2610.07232v1 Announce Type: new Abstract: Accurate short-term load forecasting (STLF) is essential for the reliable and efficient operation of modern power systems. While time series foundation
arXiv:2610.08101v1 Announce Type: new Abstract: Shared memory coordinates agents' actions, but correct records do not establish that those actions satisfy task requirements. Memory governance and fail
The RPA-era ROI model misses most of the value agentic automation creates. This post gives AI center of excellence leaders a framework to size the full value of agents across time savings, exception h
arXiv:2610.08132v1 Announce Type: cross Abstract: Concept drift threatens production machine learning, yet the empirical behavior of multivariate two-sample drift detectors at scale remains under-char
arXiv:2610.06854v1 Announce Type: cross Abstract: Synthetic data generation is critical for privacy compliance, machine learning augmentation, and software testing. While single-table evaluation is we
arXiv:2610.08533v1 Announce Type: new Abstract: Geometric alignment scores based on Gram determinants provide a compact way to model higher-order consistency among modalities, yet how such scores resp
arXiv:2610.07023v1 Announce Type: new Abstract: Large Language Models (LLMs) have achieved remarkable capabilities but remain vulnerable to jailbreak attacks that elicit harmful or unsafe outputs. Exi
arXiv:2610.07891v1 Announce Type: new Abstract: Humanoid whole-body teleoperation translates human motion into stable robot behavior in real time. Existing systems typically rely on online motion reta
arXiv:2610.07601v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) provides a natural framework for adapting pretrained models to video temporal grounding, where gen
arXiv:2610.07105v1 Announce Type: cross Abstract: Recommendation recursive self-improvement (Rec-RSI) feeds recommender outputs into subsequent training. Evaluating each round solely through its lates
arXiv:2610.07629v1 Announce Type: new Abstract: Co-design methods optimize a robot's body and controller jointly and judge the result by one number, the task reward of the fully optimized pair. That n
arXiv:2603.15822v2 Announce Type: replace Abstract: Automated radiology report generation from 3D CT volumes often suffers from incomplete pathology coverage. We provide empirical evidence that this l
arXiv:2610.08173v1 Announce Type: cross Abstract: Automated Program Repair (APR) with language models is usually evaluated by whether a generated patch passes the test suite, which can hide difference
arXiv:2610.06945v1 Announce Type: new Abstract: Mechanistic interpretability often relies on the Linear Representation Hypothesis (LRH), which assumes that high-level concepts are encoded as linear di
arXiv:2610.08109v1 Announce Type: new Abstract: Cardiac magnetic resonance imaging reconstruction aims to recover high-quality images from undersampled acquisitions, enabling faster scans while preser
arXiv:2610.08123v1 Announce Type: cross Abstract: End-to-end planners based on waypoint regression achieve strong open-loop accuracy, but they primarily learn to mimic expert geometry and remain diffi
arXiv:2610.07594v1 Announce Type: cross Abstract: Humanoid household manipulation requires the arms to act while the body balances, steps and changes posture. We present BiGym 2.0, an adaptation of Bi
arXiv:2610.07614v1 Announce Type: new Abstract: We evaluate whether AI agents can match the reported findings of published biomedical studies using public data. Existing evaluations do not consistentl
arXiv:2610.07686v1 Announce Type: new Abstract: We introduce BluffJAX: an open-source suite of adversarial imperfect information games in JAX. We provide canonical implementations of games designed fo
arXiv:2503.22764v3 Announce Type: replace-cross Abstract: The large language model (LLM) is typically integrated into the mainstream optimization protocol. However, it remains underexplored whether ma
arXiv:2610.06972v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in visual understanding and multimodal reasoning, yet they remain fun
Both embeddings models from Perplexity.ai—referred to as *pplx‑embed‑v2*—are publicly available on Hugging Face under the “perplexity‑ai” collection. The models can be accessed via the Hugging Face pa
arXiv:2610.07052v1 Announce Type: new Abstract: Whole-body tracking has become the interface through which operators drive humanoid robots, yet the references it consumes are recorded on level ground
Btw, we're hiring. We're hiring the best engineers in the world. You're ambitious. Want to make something different. You learn and build fast. Our company is growing fast, so you need to grow even fas
The biggest barrier to AI adoption isn't awareness. It's the gap between talking about AI and building with it. Here's the playbook we used to turn non-technical, customer-facing professionals into co
arXiv:2610.08790v1 Announce Type: new Abstract: Single-image scene generation aims to produce a complete 3D scene mesh from a single image, including surfaces the camera did not observe. While pretrai
Wanted to share a local memory engine I built called Hillock. The main problem I had with standard local RAG was that running document parsing and vector search chewed up so much VRAM that my actual O
arXiv:2610.07668v1 Announce Type: cross Abstract: Modern cache replacement designs saturate because they operate within fixed representational structures, hand-crafted and heuristic based feature-engi
arXiv:2610.07019v1 Announce Type: new Abstract: Fiorillo v0.5 is an open model that answers typed questions with a probability for each answer. Its main specialist reads a randomized trial's article,
arXiv:2609.34577v2 Announce Type: replace Abstract: Informative Path Planning for scalar field reconstruction uses predictive uncertainty to direct sensing vehicles toward maximally informative locati
arXiv:2606.21399v2 Announce Type: replace Abstract: Runtime oversight often intervenes when an LLM agent's calibrated failure score crosses a threshold. Yet states with the same failure risk can diffe
arXiv:2610.07175v1 Announce Type: new Abstract: Visual latent reasoning compresses rendered derivations into compact intermediate states, reducing textual reasoning overhead. Existing approaches diffe
arXiv:2610.07972v1 Announce Type: new Abstract: Mobile GUI agents increasingly operate on interfaces influenced by users' histories and preferences, but their reliability across different users remain