Knowledge catalogue
arXiv:2512.17730v2 Announce Type: replace Abstract: Detectors of AI-generated images tend to inherit the biases of the data they are trained on: models fitted to GAN imagery learn to treat GAN-specifi
arXiv:2512.13095v3 Announce Type: replace Abstract: To address the limited capability expansion and low sample efficiency of Reinforcement Learning (RL), recent methods have integrated ''hints'' into
arXiv:2507.13727v2 Announce Type: replace Abstract: Adversarial training is a promising strategy for enhancing robustness against adversarial attacks, but its impact on generalization under substantia
arXiv:2608.23217v1 Announce Type: cross Abstract: Fast and reliable plasma equilibrium prediction is essential for real-time tokamak operation and control, but conventional Grad-Shafranov (GS) solvers
arXiv:2607.14393v2 Announce Type: replace-cross Abstract: Human-in-the-loop Reinforcement Learning has become a popular approach for training, finetuning, and aligning robot behavior with user prefere
arXiv:2608.22363v1 Announce Type: new Abstract: Medical visual question answering (VQA) is a crucial task in clinical AI, yet its evaluation has so far centered almost exclusively on English, limiting
arXiv:2608.21577v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) are increasingly deployed in high-stakes domains where fairness is a critical safety requirement. In practice
David Gewirtz / ZDNET: Anthropic merges the memory systems for Claude chat and Claude Cowork, making Claude chat history available to Cowork unless users opt out — ZDNET's key takeaways — Claude chat
Artificial intelligence startup Anthropic PBC announced today it’s changing how Claude, its flagship AI product, uses memory by allowing users to see everything it remembers “topic by topic,” and edit
arXiv:2608.23283v1 Announce Type: new Abstract: General-purpose language models can reason and synthesize knowledge, but complex work also requires sustained interaction with files, information source
arXiv:2608.22894v1 Announce Type: cross Abstract: Arabic harmful-language detection has received considerable attention, yet Arabic text detoxification remains underexplored. We introduce AraDetox, a
arXiv:2608.22478v1 Announce Type: cross Abstract: Implied volatility surfaces summarise the option market and are central to many financial applications. Forecasting their future evolution requires mo
arXiv:2608.21747v1 Announce Type: cross Abstract: LLM-based coding agents generate complete software systems from high-level descriptions, yet little is known about how the format of architecture spec
arXiv:2603.29902v2 Announce Type: replace Abstract: Interleaved text-and-image generation represents a significant frontier for Multimodal Large Language Models (MLLMs), offering a more intuitive way
arXiv:2608.22160v1 Announce Type: new Abstract: Physical automation is scaling toward fleets of embodied machines commanded by an AI brain. Early deployments already run factories and warehouses at pr
sycl : mark tq2_0 as not supported (#27660) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/42777546 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Sili
grammar : parse - in char classes as literal hyphen (#27591) grammar : accept '-' escape in character classes gbnf_escape_char_class() escapes '-' as '-' but parse_char() rejected that escape, so gene
sync : ggml Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/42810281 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DI
llama.cpp : bump version to 0.3.0 (#27696) llama.cpp : bump version to 0.3.0 ci : update release default desc scripts : add prompt for generating release summary Website: https://llama.app Attestation
metal : null-check buffer alloc to fix OOM crash (#25371) metal : null-check ggml_metal_buffer_init result to avoid OOM crash ggml_backend_metal_buffer_type_alloc_buffer used the result of ggml_metal_
chat : scope qwen3-coder workarounds (#27679) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/42919681 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Si
rpc: support apple RDMA as an RPC transport (#26421) rpc: support apple RDMA as an RPC transport remove set_tensor micro optimization, rpc socket pinning per CR remove transparent reconnect trigger ap
ci : update OS used for ROCM to Ubuntu 24.04 (#27681) This matches what other build targets use and also what AMD advertises wheels as supporting. Website: https://llama.app Attestations: https://gith
kleidiai: Rework KleidiAI Build System/Integration (#26077) Rework KleidiAI Build System/Integration Signed-off-by: Jonathan Clohessy Jonathan.Clohessy@arm.com Add fp16 guard, and fix cmake caching is
arXiv:2608.21880v1 Announce Type: new Abstract: Bangla large language model (LLM) safety is difficult to evaluate with English-centric or standard-script benchmarks because Bangla users routinely writ
arXiv:2608.23213v1 Announce Type: new Abstract: This work presents an automatic bee entrance monitoring system based on YOLO11 transfer learning and the ByteTrack tracking algorithm. The study investi
arXiv:2503.18484v3 Announce Type: replace-cross Abstract: Evaluating the multilingual capabilities of Large Vision-Language Models (LVLMs) remains challenging because most benchmarks rely on non-paral
arXiv:2608.21693v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) LLMs scale model capacity efficiently through sparse activation, but their large expert parameter footprint, routing imbalance,
arXiv:2607.10358v2 Announce Type: replace-cross Abstract: Foundation models are increasingly used as image feature extractors for mammography, but their robustness under external domain shift remains
arXiv:2608.21503v1 Announce Type: cross Abstract: A verification substrate is more credible when exposing errors in its own claims, not just model outputs. GBI-DCSE v3 falsified an architectural claim
arXiv:2509.05346v3 Announce Type: replace Abstract: While large language models (LLMs) are increasingly being adopted to support personalized learning, there remains limited understanding of how their
arXiv:2508.18646v3 Announce Type: replace Abstract: Despite their rapid advancement, large language models (LLMs) suffer from a critical disconnect between benchmark scores and real-world utility. Cur
arXiv:2608.22322v1 Announce Type: new Abstract: Low-precision optimizer-state methods are commonly designed for dense Adam-style moments, but memory-efficient optimizers maintain factored, confidence-
arXiv:2608.22753v1 Announce Type: new Abstract: Large language models (LLMs) excel at text understanding and generation, yet still struggle to reliably understand and apply externally provided procedu
arXiv:2608.21541v1 Announce Type: cross Abstract: KV-cache compression is often justified by attention maps with a few large weights. This is incomplete: large weights may not contain most of the mass
arXiv:2608.22830v1 Announce Type: new Abstract: Deploying LLMs for enterprise Text-to-SQL is bottlenecked less by the model than by what context reaches it: business logic spans thousands of tables, a
arXiv:2608.21384v1 Announce Type: cross Abstract: Modern multilingual tokenizers often fragment Ukrainian and other underrepresented Cyrillic-script languages more heavily than English, creating dispa
arXiv:2608.23047v1 Announce Type: cross Abstract: Misinformation that cites legitimate papers can be especially harmful when it distorts what those studies actually report. While existing automatic fa
arXiv:2608.22232v1 Announce Type: new Abstract: Real-world situation appearances can deviate from their underlying physical states, challenging the reliability of multimodal large language models (MLL
arXiv:2608.21927v1 Announce Type: cross Abstract: Zero-cost proxies enable neural architecture search (NAS) to rank candidate networks from statistics computed at initialization, avoiding repeated tra
arXiv:2608.21864v1 Announce Type: cross Abstract: The current progress of Clinical Vision Large Language Models (C-VLLMs) has substantially improved digital diagnostics, still these frameworks often e
arXiv:2608.22557v1 Announce Type: cross Abstract: Existing LLM unlearning methods struggle with robustness: unbounded forget losses degrade model coherence, fixed-weight balancing cannot adapt as reta
arXiv:2608.22129v1 Announce Type: new Abstract: Cubic-regularized Newton methods have the optimal O(arepsilon^{-3/2}) global rate and an automatic saddle-escape mechanism, but their subproblem is most
arXiv:2608.22975v1 Announce Type: new Abstract: Embodied multimodal agents must answer from growing observation streams under a fixed per-decision token budget. We formalize this constraint through fo
arXiv:2608.21950v1 Announce Type: cross Abstract: Arabic automatic speech recognition (ASR) faces unique challenges due to diglossia, extensive regional dialect variation, and limited speech resources
arXiv:2608.21937v1 Announce Type: new Abstract: Incremental Object Detection (IOD) aims to enable detectors to continuously learn novel categories while preserving previously acquired knowledge. Howev
arXiv:2608.22708v1 Announce Type: new Abstract: Tool use in LLM systems faces a structural trade-off. Progressive disclosure keeps the prompt small by showing only the tools relevant to the current ta
arXiv:2608.21748v1 Announce Type: new Abstract: Verifier-guided text-to-image systems increasingly use test-time search to select, refine, or stop among multiple candidates, yet release thresholds are
arXiv:2608.01033v2 Announce Type: replace-cross Abstract: Language models small enough to run on a handset, quantized to a few bits, are increasingly capable of acting on their user's behalf -- which
arXiv:2608.21606v1 Announce Type: new Abstract: Machine unlearning aims to remove the influence of targeted training data from a model while preserving its remaining capabilities, but evaluating wheth
arXiv:2502.03696v2 Announce Type: replace-cross Abstract: Recent studies have demonstrated that learned Bloom filters (LBFs), which combine machine learning with the classical Bloom filter, can achiev
arXiv:2608.22808v1 Announce Type: new Abstract: When can an agent failure be caught? An audit is usually limited by the record rather than by the method. CatchBench therefore puts one auditor's questi
arXiv:2608.22577v1 Announce Type: new Abstract: Long-horizon GUI agents can retain a complete interaction trace cheaply as textual action records, but expose only a few past events to the policy in hi
arXiv:2608.21504v1 Announce Type: new Abstract: The rapid advancement of large language models (LLMs) has led to increasing interest in their application to scientific domains such as chemistry. Howev
arXiv:2608.21629v1 Announce Type: new Abstract: Cheque fraud is a material risk in after-hours business deposit operations because funds may be released within one business day, while cheque clearing
arXiv:2608.21497v1 Announce Type: cross Abstract: Biochemical recurrence (BCR), defined as any detectable prostate-specific antigen level after prostatectomy with confirmatory elevation, is widely use
arXiv:2608.22483v1 Announce Type: new Abstract: Large Language Models (LLMs) increasingly support decision-making in high-stakes domains, but they often hallucinate and express confidence that is misa
arXiv:2608.22510v1 Announce Type: new Abstract: Agent benchmarks often evaluate only final answers even when agents run on stateful runtimes. We argue this under-specifies what is being evaluated: the
arXiv:2504.09421v3 Announce Type: replace-cross Abstract: Recent advances in reasoning with large language models (LLMs)has shown remarkable reasoning capabilities in domains such as mathematics and c
arXiv:2608.22100v1 Announce Type: new Abstract: Construction robotics and automation offer promising means of improving productivity, alleviating workforce shortages, and reducing workers' exposure to