Knowledge catalogue
At Box, we've been testing Opus 5.5 on a variety of complex enterprise knowledge work tasks dealing with unstructured data with the Box Agent. Overall, we saw frontier capability levels, with major pe
arXiv:2602.04125v2 Announce Type: replace-cross Abstract: Modern digital platforms use contextual bandits to allocate valuable exposure and opportunities among competing participants. Fair treatment i
arXiv:2609.22141v1 Announce Type: cross Abstract: Automated seizure detection from scalp electroencephalography (EEG) is difficult because seizure morphology varies among patients and seizure samples
arXiv:2609.23053v1 Announce Type: new Abstract: A RAG system can hand you the right answer and cite a source it did not actually use. Models output these unfaithful citations via post-rationalization:
arXiv:2609.24218v1 Announce Type: new Abstract: Audio-based localization provides a low-cost and illumination-independent sensing solution for anti-UAV early warning. However, existing methods typical
arXiv:2609.23232v1 Announce Type: cross Abstract: Bayesian graph alignment estimates correspondence probabilities, but convergence of an alignment-score trace need not imply accurate correspondence ma
arXiv:2609.23039v1 Announce Type: new Abstract: LLM-based AI systems answer political questions for hundreds of millions of people. Current audits measure what they say to an average user, but their b
arXiv:2609.24629v1 Announce Type: new Abstract: A/B testing requires large sample sizes, long timelines, and significant costs. When auxiliary predictions of experimental outcomes are available from m
arXiv:2609.22584v1 Announce Type: new Abstract: As industrial processes grow in complexity, traditional Proportional-Integral-Derivative (PID) controllers are often insufficient for handling their non
arXiv:2609.23979v1 Announce Type: cross Abstract: Attention encoder-decoder (AED) Speech Foundation Models achieve strong ASR performance but can generate acoustically unsupported text when inputs con
Olivia Poh / Bloomberg: Australian healthcare AI startup Heidi raised 340M, including a 100M Series C led by Blackbird at a 900M valuation, taking its total funding to 430M+ — Heidi, an artificial int
arXiv:2609.22302v1 Announce Type: new Abstract: Medical vision-language models can propose how urgently a skin lesion should be reviewed, but the local service retains authority to accept or replace t
arXiv:2310.00436v2 Announce Type: replace Abstract: Authorship identification uses patterns in writing to infer who wrote a text, but those patterns also reflect topic, genre, and register. This surve
arXiv:2609.22592v1 Announce Type: cross Abstract: Training agents with reinforcement learning requires a gym, comprising a task, an executable environment in which the task can be attempted, and a ver
arXiv:2609.24059v1 Announce Type: new Abstract: Semantically meaningful subtask labels can provide useful contexts for long-horizon policies, but automatically identifying both reliable temporal bound
arXiv:2609.22971v1 Announce Type: new Abstract: Evaluating user experience (UX) on live websites through user testing is expensive, subjective, and difficult to scale. LLM agents offer a promising rou
arXiv:2609.22701v1 Announce Type: new Abstract: Manufacturing AI systems must autonomously adapt to continuous distributional shift from raw-material variability, ambient changes, and equipment aging,
arXiv:2609.22913v1 Announce Type: new Abstract: Talking-head and dyadic models now achieve real-time inference, yet fast motion generation alone does not produce an interactive conversation. A live sy
arXiv:2609.22635v1 Announce Type: cross Abstract: Three-dimensional fetal brain ultrasound offers non-ionizing, cost-effective imaging with rich spatial information for comprehensive anatomical assess
metal : fix mask bounds in flash attention block pre-pass (#29220) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/49087452 macOS/iOS: macOS Apple Silicon (
vendor : update cpp-httplib to 0.57.1 (#29239) Signed-off-by: Adrien Gallouët adrien@gallouet.fr Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/49092442 ma
hexagon: new HMX-optimized GATED_DELTA_NET (#29199) hex-gdn: start putting together HMX support for GDN hex-gdn: working hmx but not-pipelined and slow for now hex-gdn: re-write vtcm layout handling a
opencl: add A8 Q4_0 non-MoE dp4a binary kernel (#29055) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/49141307 macOS/iOS: macOS Apple Silicon (arm64) macO
ci : publish snapdragon builds in release workflow (#29007) The snapdragon CI builds packages only to feed the QDC device tests, so Hexagon NPU binaries never reached the releases page. Build both tar
chat : Fix Muse Glimmer tool-call first parser error (#29242) Fix Muse Glimmer tool-call first parser error Add test to verify Condense patterns remove test for trigger patterns Website: https://llama
cmake : allow repeated find_package calls for llama (#29228) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/49213556 macOS/iOS: macOS Apple Silicon (arm64)
convert: add MiMo-V2.6 support (#29257) convert: add MiMo-V2.6 support Hoist the K3 mxfp4 conversion repack into base.py so it can be reused Remove decoder from mmproj convert Update conversion/mimo.p
spec : support DFlash for HunyuanOCR (#28890) model : add DFlash layer-input taps for HunyuanVL DFlash speculative decoding needs the target graph to expose the residual stream entering each layer (re
server: Add support for binding to multiple addresses (#28690) Add support for binding llama-server to multiple addresses Assisted-by: Codex remove redundant thread handler make it clear about overlap
jinja: use const for statement::execute and ::visit (#29271) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/49279983 macOS/iOS: macOS Apple Silicon (arm64)
ggml : IQ1_M build prefix sums once per block (#28706) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/49294443 macOS/iOS: macOS Apple Silicon (arm64) macOS
metal : gate mul_mm_id src1 rescale behind ggml_prec (#29029) metal : gate mul_mm_id src1 rescale behind ggml_prec Assisted-by: Claude Fable 5.1 ggml-webgpu: reject MUL_MAT_ID when src1 precision is F
mtmd: add various sanity checks (#29276) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/49308522 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon
vulkan: add Intel Xe flash attention optimization kernels (2/3, Xe-LPG Plus/Xe2/Xe3) (#24406) vulkan : Intel FA kernel optimization for split k path vulkan : Host code update for Intel split k FA kern
server: support input_image in function_call_output (#20663) (#22575) server: support input_image in function_call_output (#20663) server: fix if statement spacing server: avoid repeated type lookup W
server: do not pass log file to children (#29212) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/49344105 macOS/iOS: macOS Apple Silicon (arm64) macOS Appl
server: fix router eviction races with the existing queue (#29217) server: route every model load through the queue A model loaded by the fast path has no queue entry, so tick() evicts it at its LOADE
opencl: add bin kernel kernel_gemm_noshuffle_q4_k_q8_1_dp4a_ila_a8_bin (#29056) opencl: add A8 Q4_K non-MoE dp4a binary kernel opencl: rename binary kernel selection helpers Website: https://llama.app
arXiv:2609.23490v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly execute multi-step workflows through tool use and interaction with users and environments. However, curre
arXiv:2511.18921v2 Announce Type: replace Abstract: Backdoor attacks undermine the reliability and trustworthiness of machine learning systems by injecting hidden behaviors that can be maliciously act
arXiv:2607.15207v2 Announce Type: replace Abstract: World-action models (WAMs) are emerging as a promising foundation for embodied control: rather than predicting actions alone, they learn representat
arXiv:2609.22124v1 Announce Type: new Abstract: This paper describes the system submitted to the UNLP 2026 Shared Task on Multi-Domain Document Understanding. The challenge required extracting precise
Cybersecurity company Barracuda Networks Inc. today launched Barracuda AI Data Security, a product that monitors and controls what company data employees feed into artificial intelligence tools. The r
arXiv:2609.22885v1 Announce Type: new Abstract: Safe operation of robotic systems requires trajectories to remain within a prescribed safe set under admissible control inputs. Barrier certificates pro
arXiv:2609.23896v1 Announce Type: new Abstract: Control barrier functions (CBFs) have become one of the most popular tools for encoding and enforcing state constraints in safety-critical robotics. Sta
arXiv:2609.23212v1 Announce Type: cross Abstract: The Deck-of-cards-based Ordinal Regression (DOR) infers a value function from a ranking of reference alternatives in which the Decision Maker (DM) ins
arXiv:2609.23383v1 Announce Type: cross Abstract: Bayesian filtering provides a principled framework for online state estimation under uncertainty, yet its application to systems with high-dimensional
arXiv:2609.24140v1 Announce Type: new Abstract: Neural-rendering-based SLAM relies on rendered RGB-D residuals for camera tracking and map optimization, but the reliability of these predictions can va
arXiv:2609.22730v1 Announce Type: new Abstract: Robot manipulation tasks often involve hidden state information that cannot be directly observed and must be inferred through sequential physical intera
arXiv:2609.22608v1 Announce Type: new Abstract: Projectile interception is a challenging dynamic manipulation problem. Intercepting a thrown object with a robot arm requires reaching a point on the ob
arXiv:2609.22633v1 Announce Type: new Abstract: Bilingual language models (LMs) offer a controlled setting for studying how training conditions shape second-language (L2) behaviour, but prior work typ
arXiv:2609.22404v1 Announce Type: new Abstract: Over the last decade, behavior trees (BT) have become one of the dominant behavior models for coordinating missions of robotic systems. Yet empirical ev
arXiv:2609.23789v1 Announce Type: new Abstract: Modern conditional generative models face significant challenges when learning complex covariate dependencies. While sufficient dimension reduction (SDR
arXiv:2609.22583v1 Announce Type: new Abstract: Predictive maintenance in Industry 4.0 refers to using data from sensors, machines, and production systems to estimate when equipment is likely to fail,
arXiv:2609.24190v1 Announce Type: new Abstract: Artificial intelligence (AI) has advanced at a rapid pace in recent years. Initially, breakthroughs in large language models caught widespread attention
arXiv:2609.22127v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to draft contractual language, yet conventional accuracy or preference-based evaluations are poorly m
arXiv:2609.23650v1 Announce Type: cross Abstract: Vision-language-action (VLA) models have achieved strong performance in embodied manipulation, but still lack a clear mechanism to balance behavioral
arXiv:2609.22820v1 Announce Type: new Abstract: Average squared error cannot reveal whether forecasting performance degrades because the future becomes less predictable or because forecasts move farth
arXiv:2609.24215v1 Announce Type: new Abstract: Although text-to-image models can accurately depict subjects and scenes, creators still struggle to specify the fine-grained emotions an image should co
arXiv:2609.22767v1 Announce Type: new Abstract: The IEEE BigData Cup benchmark combines three prediction problems with different output structures: ordinal suicide-risk classification, multi-label psy