Knowledge catalogue
arXiv:2610.36785v1 Announce Type: new Abstract: Multi-view tracking extends visual coverage beyond a single camera, providing complementary observations when targets are occluded or leave the view. Th
arXiv:2610.36999v1 Announce Type: cross Abstract: Field applications in chemical sensing, from portable safety monitors to mobile robots, require models that are lightweight, fast to respond, and can
arXiv:2610.37361v1 Announce Type: cross Abstract: We study online interval selection with binary predictions of membership in a final optimal solution. Requests arrive in arbitrary order; accepted req
arXiv:2610.36598v1 Announce Type: new Abstract: Handheld data-collection interfaces such as the Universal Manipulation Interface (UMI) allow manipulation demonstrations to be gathered in the wild with
arXiv:2610.36896v1 Announce Type: new Abstract: We present PREEN (Preset Regression via an Exemplar-based Editor Network), which casts color style transfer as regression onto the 29 parameters of a de
arXiv:2610.36967v1 Announce Type: new Abstract: Proactive LLM agents anticipate service opportunities from ongoing observations and accumulated history. Existing approaches emphasize recent context or
arXiv:2610.36689v1 Announce Type: new Abstract: Self-disclosures on the Web support diverse psychological analyses, from recognizing expressed experiences to identifying symptom-relevant information.
arXiv:2610.36703v1 Announce Type: new Abstract: Multivariate time series forecasting plays a critical role in Web and cyber-physical systems, where large-scale services and IoT infrastructures generat
arXiv:2610.37111v1 Announce Type: new Abstract: Active simultaneous localization and mapping (SLAM) addresses the problem of planning robot motion to build complete and accurate maps of unknown enviro
arXiv:2610.36743v1 Announce Type: new Abstract: Event-triggered recording needs a useful combination of target capture and false triggers, yet representation comparisons can change with readout and th
arXiv:2610.37566v1 Announce Type: new Abstract: Injecting new subjects naturally during streaming video generation requires integrating newly supplied visual references into the existing video while p
arXiv:2609.34717v2 Announce Type: replace Abstract: Open-weight large language models (LLMs) can generate function-level programs from natural-language prompts, but plausible candidates still fail on
arXiv:2610.36831v1 Announce Type: new Abstract: Leading GUI grounders score 93 to 96% on ScreenSpot-v2, and reported gaps between new and prior models are about a point. At this level the useful quest
arXiv:2610.36533v1 Announce Type: cross Abstract: Recently, LLM-based autonomous agents have shown strong capabilities in iteratively generating, evaluating, and refining executable solutions. In robo
arXiv:2603.18520v2 Announce Type: replace Abstract: Electric vehicles (EV) create an urgent need for scalable battery recycling, yet disassembly of EV battery packs remains largely manual due to high
arXiv:2610.36755v1 Announce Type: cross Abstract: Gradient-based data attribution has become an important tool for high-quality data selection in the instruction fine-tuning of large language models (
arXiv:2603.11137v2 Announce Type: replace-cross Abstract: On-policy distillation (OPD) is a promising approach for transferring reasoning capabilities to capacity-constrained models, yet sampled-token
arXiv:2610.37326v1 Announce Type: new Abstract: Existing evaluations of text-conditioned 3D indoor scene generation largely emphasize semantic fidelity and physical validity at rest, leaving interacti
arXiv:2603.29109v2 Announce Type: replace-cross Abstract: Large language models (LLMs) can describe what a piece of code should compute, but they do so in free-form text. Such text cannot be checked a
arXiv:2610.36807v1 Announce Type: cross Abstract: Rubric-based reinforcement learning uses fine-grained grader feedback to train large language models on open-ended tasks, but grader randomness can al
arXiv:2610.36715v1 Announce Type: cross Abstract: Neural music editing requires a system to perform a requested change while preserving the musical content that should remain unchanged. Existing evalu
arXiv:2610.36650v1 Announce Type: new Abstract: Graph-structured representations of text data have become foundational across machine learning, yet it remains unclear how to systematically construct a
arXiv:2610.37576v1 Announce Type: new Abstract: Diffusion-based denoising commonly uses Gaussian perturbations, whereas sensor noise follows diverse signal-dependent statistical laws. In this paper, w
arXiv:2411.19193v3 Announce Type: replace-cross Abstract: Many operations run on a budget that must rarely run out, such as a wear allowance. A wrapper keeps the remaining budget in the state, subtrac
arXiv:2610.37666v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have made substantial progress in robotic manipulation, but their generalization remains constrained by the divers
arXiv:2610.37218v1 Announce Type: new Abstract: Functional segmentation requires locating small interactive parts, such as knobs, buttons, and sockets, in indoor point clouds and returning confidence-
Unsurprisingly, you can’t get an honest assessment of Tesla’s safety, cost, operating cost, or reliability from MSM. Tesla doesn’t pay them to say nice things. AI chat, including Grok, will just summa
Utah gave Claude Code to 34 developers across 10 state agencies. 80% had a working environment within 30 minutes, 71% reported saving 20+ hours by the end of the four-week pilot. We're expanding our p
arXiv:2610.36850v1 Announce Type: new Abstract: Evaluation of Tamil handwritten character recognition (HCR) has largely focused on clean test images, and a standardized multi-corruption robustness ben
We’re working to build the largest collection of private and public practitioner evals. Today, 31 new partners join the Specialized Intelligence Index. Compare open, closed, and specialized models on
arXiv:2610.36852v1 Announce Type: new Abstract: Robot foundation models may generalize across tasks and embodiments, but their actions still depend on sensors that can fail. When the policy is frozen
arXiv:2610.37658v1 Announce Type: new Abstract: Test-time adaptation helps a deployed model respond to changing inputs, but the same intervention can rescue one batch and damage the next. Updating nor
arXiv:2610.36826v1 Announce Type: new Abstract: Autonomous agents increasingly depend on harnesses that govern interaction, memory, tools, and execution around large language models (LLMs). While rece
I've been building OpenJet, a local coding agent with its own CUDA megakernel engine for Qwen3.8-27B Q4_K_M. Until now it served one conversation at a time. The new release serves several agents at on
arXiv:2610.35729v1 Announce Type: cross Abstract: Imagery captured by unmanned aerial vehicle (UAV) systems increasingly raises privacy concerns, as UAV aerial surveillance routinely captures sensitiv
arXiv:2610.34044v1 Announce Type: cross Abstract: Entropy in reinforcement learning with verifiable rewards (RLVR) moves up or down depending on choices that should be neutral, such as whether over-le
A source said that the Guardians were open to allowing Vogt the Mariners opening, but he preferred to stay in Cleveland Sources: The Mariners are bringing in Joe Espada and Jason Kanzler to Seattle th
arXiv:2603.07949v3 Announce Type: replace-cross Abstract: VLA models have emerged as the mainstream for embodied intelligence, which decouples reasoning and execution via action chunks. To enable real
arXiv:2610.34529v1 Announce Type: cross Abstract: Background/Objectives: Rapid differentiation of ischemic and hemorrhagic stroke subtypes is vital for acute management. Although current deep learning
arXiv:2610.34634v1 Announce Type: cross Abstract: Reusable Web-agent verification requires a rule to follow changing requirements and support subsequent execution. We introduce AgentProofBench, which
arXiv:2610.33130v1 Announce Type: new Abstract: Human activity recognition benchmarks underrepresent culturally situated forms of movement and interaction. We introduce Ampe-DB, a multimodal dataset b
Felix Rieseberg: An Anthropic hiring manager says he stopped giving coding interviews because Claude is better at them and tells junior engineers that “hunger beats tenure” — This month, I laid the tr
Anthropic: Anthropic expands its US GSA partnership to give federal, state, local, tribal, and territorial governments a 40% discount on Claude, estimated to save $1B — We are expanding our partnershi
anyway here's my soundcloud https://x.com/latentspacepod/status/2115156080309489736 How Anthropic ships Claude with Claude https://latent.space/p/opus55/ Opus 5.5 is the #1 LLM in the world right now.
arXiv:2610.35083v1 Announce Type: new Abstract: AI assistants are increasingly asked to reason over a user's own web traces: group chats, community threads, activity logs and revision histories. On CL
hexagon: add GGML_HEXAGON_VTCM_SIZE (#31221) hexagon: add GGML_HEXAGON_VTCM_MB and GGML_HEXAGON_NTHREADS caps Change-Id: Idffe1613c8db6f96aa842d43d1b2efaed45462a8 hexagon: rename VTCM cap to GGML_HEXA
opencl: initial support for q3_k (#31172) opencl: add q3_k AOS mv opencl: add q3_k SOA mv and tiled mm opencl: add q3_k noshuffle gemm/gemv for adreno opencl: add q3_k dp4a gemm for adreno Co-authored
opencl: refine mul mat id -1 index (#31170) Assisted-by: Codex Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/60266382 macOS/iOS: macOS Apple Silicon (arm6
llama : remove obsolete n_pad from memory instances (#31200) Every caller passes n_pad = 1 and the only two users clamp it to 256. Drop the parameter, the members and the trivially true kv_size assert
ggml : relax scale to non-contiguous views (#31146) ggml : relax scale to non-contiguous views SCALE requires src0 to be 1D-contiguous. Relax this to dim-0 contiguity with arbitrary row strides (ggml_
ci : use ccache depend mode for ROCm release builds (#31231) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/60293667 macOS/iOS: macOS Apple Silicon (arm64)
glm5-next : QSA without kq_mask (+ DSA) (#31009) glm5-next : QSA without kq_mask DSA: dsa top-k mask change tested with layers 0,3 of DeepSeek-V3.2 Website: https://llama.app Attestations: https://git
metal : add GGML_OP_TOP_K_MASK (#31230) metal : add GGML_OP_TOP_K_MASK Port the fused top-k mask from the CUDA backend: a grid-stride kernel fills the output with -inf, then one threadgroup per row co
mtmd-cli: Reduced scope of batch pointer (#31155) (#31165) mtmd-cli: Reduced scope of batch pointer (#31155) mtmd-cli: Remove CLI regression test Website: https://llama.app Attestations: https://githu
vulkan: fix CI llvmpipe by allowing dim 3 broadcast in MUL_MAT (#31239) vulkan: allow dim 3 broadcast in MUL_MAT supports_op rejected every MUL_MAT whose src0 and src1 differ in ne3, although mul_mm,
rpc : catch std::length_error in recv_msg (#31204) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/60485441 macOS/iOS: macOS Apple Silicon (arm64) macOS App
llama : build the k-pool sparse selection independently of the kq_mask shape (#31243) llama : build the k-pool sparse selection independently of the kq_mask shape qwen4exp (QSA) and glm5-next pick cac
Release [2026/10/27] 🚀 We release Unlimited OCR 2, achieving unlimited-horizon parsing with SR-SWA. What's New in 2 Sparse Reference Sliding Window Attention (SR-SWA): Compresses text-visual attention
arXiv:2606.18785v2 Announce Type: replace-cross Abstract: Identifying Pareto optimal solutions is critical to support multi-objective decision-making. In this work, we present Top-Two Pareto Front Tho
arXiv:2610.35267v1 Announce Type: new Abstract: Natural-language-to-domain-specific-language (NL-to-DSL) semantic parsing systems increasingly translate informal user descriptions into structured arti