Knowledge catalogue
arXiv:2609.21461v1 Announce Type: cross Abstract: Embodied foundation models are constrained by the limited scale and diversity of robot demonstrations, motivating the use of large-scale egocentric hu
arXiv:2609.20974v1 Announce Type: new Abstract: In Mixture-of-Experts language models, the router typically selects and weights experts based on the token's hidden state, utilizing limited contextual
arXiv:2510.07024v3 Announce Type: replace-cross Abstract: LLMs are remarkable artifacts that have revolutionized a range of knowledge-intensive tasks. A significant contributor is their factual knowle
arXiv:2609.21284v1 Announce Type: cross Abstract: Long-running AI agents outlive initiating processes through credentials, delegated tasks, queues, callbacks, reservations, and provider-side operation
arXiv:2609.20868v1 Announce Type: cross Abstract: Transfer and multi-nucleon transfer reactions are essential tools for probing nuclear structure and reaction dynamics, requiring precise determination
arXiv:2609.21863v1 Announce Type: new Abstract: Empirical evaluation is central to recommender-systems (RecSys) research, but turning experimental designs into executable code remains a manual and err
arXiv:2609.21940v1 Announce Type: new Abstract: Long-term memory is essential for large language model (LLM) agents to maintain consistency and personalization over extended interactions. Existing mem
arXiv:2609.22048v1 Announce Type: new Abstract: A selective predictor acts as a safety gate: it returns an output only when the prediction appears sufficiently trustworthy. Deployments increasingly re
arXiv:2609.21377v1 Announce Type: new Abstract: Robotic fabric comparison needs to actively combine visual appearance and tactile cues. Here, we present AVT-Fabric, an RGB-first framework that allocat
Amazon Web Services Inc. says it’s trying to help developers solve the problem of scaling artificial intelligence agents to cloud environments with the launch of Strands Harness, an open-source agent
webgpu : add fused gdn + cpy (#28976) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/48873164 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (a
metal : fix deprecation warnings from macOS 27 SDK (#29136) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/48890258 macOS/iOS: macOS Apple Silicon (arm64)
cuda : tune MMVQ to MMQ crossover for SM70 (Volta) (#28912) tune MMVQ to MMQ crossover for SM70 (Volta) Signed-off-by: Yangyu Chen cyy@cyyself.name Apply suggestion from @JohannesGaessler Apply sugges
hexagon: overhaul of buffer and DMA handling to support 64bit mappings + improvements (#29197) hex-dma64: enable support extended buffer mappings and 64bit dma hex-dma64: expand binary ops to support
ci : Upgrade CUDA to 13.4 for Ubuntu CUDA Release Builds (#29202) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/48951751 macOS/iOS: macOS Apple Silicon (a
sycl : coalesce MKL-FA softmax loads instead of one work-item per row (#28918) sycl : coalesce MKL-FA softmax loads instead of one work-item per row better human readable variable name Website: https:
json: Fixed json enum handling (#28518) Fixed json enum handling Added common_json_value handling for enum values. Added tests/test-json.cpp to cover testing of some aspects of common_json. Removed te
ggml-metal : simplify fusion pattern op list declaration (#29206) ggml-metal : derive non-empty fusion ops from ops_all Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp ggml-metal : drop _all su
tests : remove stale comment (#29140) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/48998612 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (a
server : do not forward --api-key-file to router-spawned child instances (#28938) In router mode, authentication belongs to the router. unset_reserved_args() already unset LLAMA_API_KEY, but did not u
args: add env vars for temperature, top-p, min-p and penalties (#27380) Allow configuring --temp, --top-p, --min-p, --repeat-penalty, --presence-penalty and --frequency-penalty via LLAMA_ARG_* so llam
tests/test-backend-ops : allow regex entries in the -o filter (#29204) tests/test-backend-ops : allow regex entries in the -o filter so far -o only accepted a comma separated list of exact op names or
test-llama-archs : make tensor data stdev configurable and improve help (#29133) test-llama-archs : make tensor data stdev configurable Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp test-llam
cuda: fix sm_70 tile compilation error (#29224) The 5-argument load_ldmatrix added in 1884824 only defines tile<16,8>, so the Volta tile<8,4> does not match. See #29222 for details. Building on 188482
arXiv:2604.02401v2 Announce Type: replace Abstract: This paper revisits three backup-based safety filters -- Backup Control Barrier Functions (Backup CBF), Model Predictive Shielding (MPS), and gateke
arXiv:2609.21743v1 Announce Type: cross Abstract: Entropy minimization is a standard objective for test-time adaptation (TTA), but it can fail in imbalanced binary segmentation. Unlike image classific
Banger paper on self-evolving ontologies for agents. You just can't go wrong with implementing an ontology layer for your agents. This paper shows exactly why. The show that GPT-5.5 gains 26.7 points
arXiv:2609.21997v1 Announce Type: cross Abstract: LLM agents in social simulation revise their opinions implicitly, in context: how open an agent is to persuasion can neither be specified nor verified
arXiv:2609.21694v1 Announce Type: cross Abstract: Context: We developed a probabilistic machine learning method with the aim of performing the O(10)-way classification of low- and high-resolution spec
arXiv:2512.24493v3 Announce Type: replace-cross Abstract: Control barrier functions for port-Hamiltonian systems inherit model uncertainty when the Hamiltonian is learned from data. We show how to pro
arXiv:2601.07316v2 Announce Type: replace-cross Abstract: Automated electrocardiogram diagnosis using deep learning remains limited by signal-agnostic representations that treat multi-lead recordings
arXiv:2509.22754v2 Announce Type: replace-cross Abstract: Autonomous driving remains a highly active research domain that seeks to enable vehicles to perceive dynamic environments, predict the future
arXiv:2609.21490v1 Announce Type: new Abstract: Gender bias remains a persistent concern in machine translation (MT), affecting both generated translations and their automatic evaluation. When a sourc
arXiv:2609.21879v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have recently been proposed as promising tools for face recognition, as they can produce natural language explanations a
arXiv:2609.22055v1 Announce Type: new Abstract: A desirable property of a world model is the ability to learn continually across tasks, adapting to new environments without forgetting what the agent h
arXiv:2609.21599v1 Announce Type: new Abstract: Fraudulent job posting detection aims to identify job advertisements that are corrupted either through fake content, misleading information, or negative
arXiv:2609.21362v1 Announce Type: new Abstract: Conventional tokenizers represent text as characters or statistically derived subwords, overlooking the internal phonological structure of syllables and
arXiv:2609.21763v1 Announce Type: new Abstract: A medical model's benchmark score does not establish that the same conclusion holds under a different evaluation. This study tests whether claims about
arXiv:2609.21276v1 Announce Type: cross Abstract: In automated Printed Circuit Board Assembly (PCBA) inspection, standards-guided decisions require systems to jointly reason over fine-grained visual c
arXiv:2603.13099v3 Announce Type: replace Abstract: We introduce CRYSTAL (Clear Reasoning via Yielded Steps, Traceability, and Logic), a diagnostic benchmark with 6,372 instances that evaluates multim
arXiv:2609.21656v1 Announce Type: new Abstract: Recent Joint-Embedding Predictive Architectures (JEPAs) prevent representation collapse by constraining learned representations to follow a prescribed t
arXiv:2609.21909v1 Announce Type: new Abstract: In this work, we conduct a systematic comparison of two state-of-the-art motion-imitation reinforcement learning (MIRL) pipelines, one built on SCONE/Hy
arXiv:2609.21231v1 Announce Type: new Abstract: Reference-based metrics for Grammatical Error Correction (GEC) such as M^2 and ERRANT assume that the reference set enumerates all valid edits, and ther
arXiv:2609.20828v1 Announce Type: new Abstract: ASR systems optimised for Word Error Rate (WER) often miss named entities and filled pauses in accented conversational English, both critical for langua
arXiv:2609.20886v1 Announce Type: cross Abstract: Business intelligence (BI) is a cornerstone of enterprise decision-making and is widely used by enterprise users in software such as Power BI and Tabl
Financial Times: Big Tech is increasingly using residual value guarantees for off-balance sheet AI spend, giving Nvidia and Broadcom a way to support their customers' purchases — Wall Street finds new
arXiv:2609.21758v1 Announce Type: new Abstract: Topology optimization (TO) represents a significant step towards automating the design process: given a working simulation, TO can produce a viable prot
arXiv:2609.20904v1 Announce Type: cross Abstract: Hybrid motor-imagery brain-computer interfaces (MI-BCIs) combining EEG and fNIRS can outperform EEG-only systems by exploiting complementary electroph
arXiv:2609.20844v1 Announce Type: new Abstract: Deepresearch (DR) agents interact with real-world web environments through multi-turn search and visit, causing their contexts to grow rapidly over time
arXiv:2609.22064v1 Announce Type: new Abstract: Advances in large-scale neural recording have made it possible to collect data across many animals and distributed brain regions, raising the question o
BREAKING: Grok 4.7 dominates the Legal Agent Benchmark. It scored 19.6% on realistic, long-term legal tasks, beating every other model tested. That is nearly 3× Fable 5.1. Another major win for Grok 4
🚨 BREAKING: US Treasury Secretary Scott Bessent declares OpenAI management personally responsible for HuggingFace hack > 'The Hugging Face incident, that is the responsibility of the OpenAI management
Georgia Wells / Wall Street Journal: British Columbia sues OpenAI for alleged safety violations and negligence for failing to flag the Tumbler Ridge shooting suspect's ChatGPT activity to police — The
arXiv:2609.21422v1 Announce Type: cross Abstract: Deep representation learning often selects hidden features and fits the final predictor on the same sample, so fixed-feature analysis performed after
arXiv:2609.21619v1 Announce Type: new Abstract: On-policy distillation (OPD) improves reasoning models by learning the token-level discrepancy between a stronger teacher and an on-policy student. Howe
arXiv:2609.20981v1 Announce Type: new Abstract: Autoregressive (AR) models suffer from local greediness, while diffusion language models (DLMs) often lack the strict causal structure required for reas
I decided to do this experiment to see what would be the ability of an LLM model to, in a single shot, transfer the knowledge it may or may not have about that artist/brand/designer/animator to a comp
arXiv:2609.21157v1 Announce Type: new Abstract: Large Language Model (LLM) agents are increasingly being explored for chip design, but most existing approaches operate directly at RTL. We ask whether
https://preview.redd.it/qs228wu19yqh1.png?width=1192&format=png&auto=webp&s=76b02d846c09049c536c4e64411d5c26167e0bd7 Tried to use chat to help with an assignment, and it linked this super sketchy webs
arXiv:2609.21982v1 Announce Type: new Abstract: Robot demonstration collection often produces imperfect or failed trajectories in addition to successful demonstrations. Existing methods typically expl