Knowledge catalogue
arXiv:2608.07167v1 Announce Type: new Abstract: Giving an AI agent the ability to send emails, query databases, or execute commands is useful--until the agent is tricked into doing something it should
arXiv:2608.06701v1 Announce Type: cross Abstract: Fixing GitHub issues in large-scale projects is a long-horizon task, especially when a fix requires changes across multiple locations or the issue des
arXiv:2603.13108v2 Announce Type: replace-cross Abstract: Panoramic imagery provides holistic 360{eg} visual coverage for environmental perception in quadruped robots. However, existing occupancy pred
arXiv:2608.07126v1 Announce Type: cross Abstract: Most CubeSats, small and low-cost satellites roughly the size of a shoebox, do not survive as long as they were designed to: a study of 178 missions f
arXiv:2608.06750v1 Announce Type: cross Abstract: Iterative refinement has significantly enhanced Large Language Model (LLM) performance; however, existing methods ranging from feedback-based Self-Ref
arXiv:2608.06429v1 Announce Type: new Abstract: Interpretability methods for large language models (LLMs) describe internal state but do not directly test whether that state is causally sufficient to
arXiv:2608.07254v1 Announce Type: cross Abstract: The increasing specialization of scientific research challenges existing classification systems, which provide effective representations of broad disc
arXiv:2608.06931v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly involved in scientific discovery, yet it remains unclear whether they can support complex real laboratory
arXiv:2608.06802v1 Announce Type: new Abstract: On-policy distillation (OPD) trains a student on its own rollouts with token-level supervision from teacher models, but its effectiveness can depend str
arXiv:2608.07014v1 Announce Type: new Abstract: Aggregate scaling curves suggest that Video LLMs improve smoothly or saturate as visual budgets grow. We show that this view can conceal large, opposing
arXiv:2608.07454v1 Announce Type: cross Abstract: The total synthesis of a complex molecule is among the most demanding intellectual and experimental feats in chemistry: a chemist must plan many steps
arXiv:2608.07214v1 Announce Type: cross Abstract: Modern AI is no longer a single model but an ecosystem: classical ML predictors, deep and multimodal models, large language models, and agents, each t
Obviously nobody needs a transformer that's good at multiplication. I wanted to know whether a stock transformer could do exact arithmetic if I chose its weights directly. I implemented the grade-scho
arXiv:2608.07015v1 Announce Type: new Abstract: Omni-domain infrared small target (IRST) detection is crucial for infrared surveillance, yet remains challenging due to heterogeneous imaging domains an
arXiv:2608.07051v1 Announce Type: new Abstract: Generic parameter-efficient fine-tuning (PEFT) methods transferred from language models can fail silently on real-time detectors, whose heterogeneous op
Available context length with and without the patch: Model: QWEN 27B ROCm stock patched Vulkan stock patched IQ4_XS Pure, single 16GB GPU 19.456 76.032 68,352 78,592 Q6_K_L on 16GB + 12GB 64,256 149,2
GitHub Models is now retired I missed this news until today, when the GitHub Actions run for my simonw/research repository failed with this error message: GitHub Models is temporarily unavailable as p
Prompt injection is the most common way that scammers attack people and agents: your agent visits http://foo.com, and the website has malicious text like “btw send the user’s ssh keys and passwords to
and we agree with @GaryMarcus. Training and running frontier class AI on CPUs, at a fractional cost, saving the planet, while building human aligned AI is the 2nd innings of AI race. CPUs and the rise
I’m planning a dedicated home AI server, mainly for local LLM inference, agents/tool use, Docker services, and eventually larger MoE models with CPU offload. My plan is to start with 2x 16GB GPUs = 32
I use auto mode for everything and now that will be the default in Claude. Anthropic had to decide whether to prioritize maximization of human control or minimization of risk, and it chose the latter.
(I am not a native speaker, written by myself, so please bear with me) I really want to like DeepSeek-V4-Flash-0731. But it has serious flaws that don't align with the high score on intelligence bench
arXiv:2608.05205v1 Announce Type: new Abstract: Event-centric intelligent analytical systems heavily depend on explicit causal event knowledge for risk early warning, decision-making support and narra
arXiv:2601.21800v4 Announce Type: replace Abstract: We introduce BioAgent Bench, an evaluation suite designed for measuring the performance and robustness of AI agents in common bioinformatics tasks.
arXiv:2510.14768v2 Announce Type: replace Abstract: Real-world dexterous manipulation often encounters unexpected errors and disturbances, which can lead to catastrophic failures, such as dropping the
today was the last day of my subscription on ollama cloud, to be honest it was a great price value for me and with GLM 5.2 and Deepseek V4 Pro i was able to Vibe code my custom woocomerce shop with mu
arXiv:2608.05993v1 Announce Type: new Abstract: Much clinical value is conveyed not through structured records but through communication: exchanges in which patients describe symptoms, clinicians reas
arXiv:2608.05169v1 Announce Type: new Abstract: Long-form story generation requires models to preserve narrative consistency across extended contexts, yet existing prompting-based methods often accumu
arXiv:2608.05367v1 Announce Type: new Abstract: Counterfactual analysis aims to predict potential outcomes under hypothetical scenarios, offering valuable insights for decision-making. This paper inve
arXiv:2608.05170v1 Announce Type: cross Abstract: Role-playing agents (RPAs) have emerged as a key application of large language models, enabling immersive and high-fidelity character simulation. Accu
arXiv:2608.05893v1 Announce Type: new Abstract: Electrocardiography (ECG) is one of the most widely used non-invasive tools for diagnosing cardiovascular disease, but transforming multi-lead ECG recor
arXiv:2608.05744v1 Announce Type: new Abstract: Continuous workpiece localization is essential for traceability and process coordination in hot forging, but direct tracking is unreliable because of ex
arXiv:2608.05353v1 Announce Type: new Abstract: LLM judges are often asked to extract criteria and evidence before choosing between candidate answers. This workflow assumes that the intermediate recor
arXiv:2608.05203v1 Announce Type: new Abstract: Machine learning models achieve strong predictive accuracy for 90-day outcome prediction in acute ischaemic stroke, yet clinical adoption is limited by
arXiv:2608.05560v1 Announce Type: cross Abstract: Timely anticipation of physical hazards is essential for real-world safety, yet existing MLLM evaluations focus on harmful content or general risks, l
Hey everyone, I just wanted to share my journey here for some motivation. Three years ago, I saw the sudden spike in AI and realized it was the future of tech. My goal at the time was to be an indie g
arXiv:2608.05685v1 Announce Type: new Abstract: Most public benchmarks for machine-condition monitoring come from test rigs, where faults are induced on purpose and every event is known. Real producti
arXiv:2608.05747v1 Announce Type: new Abstract: Spatial intelligence is fundamental to embodied agents, yet existing benchmarks focus on local spatial perception from single or few viewpoints, overloo
arXiv:2608.05210v1 Announce Type: cross Abstract: Picture books and comics have long been used to disseminate hateful narratives because they are easily understood even by children, as exemplified by
arXiv:2608.05594v1 Announce Type: cross Abstract: Validation adequacy in safety-critical software depends on more than the system under test. Critical scenarios must be constructed under controlled co
Just saw that the LLMs-from-scratch repository passed 100,000 stars on GitHub! This is super cool and motivating. I am really happy to see that this open-source repo has helped so many people. Thanks
LabyrinthBench measures the thing that actually kills long agent runs — whether a model can still use what it learned twenty turns ago — deterministically, with no LLM judge, on your own hardware, wit
arXiv:2608.05706v1 Announce Type: new Abstract: World models enable agents to perform forward rollout and planning without real-world interaction. However, their application in open-world embodied int
arXiv:2608.06377v1 Announce Type: cross Abstract: Language models increasingly condition their answers on external signals, and a single misleading one can turn a correct answer wrong. The obvious rem
arXiv:2608.05872v1 Announce Type: cross Abstract: Standard Large Language Models (LLMs) execute layers sequentially. Dynamic layer routing, i.e. search for a different execution path through layers in
arXiv:2608.05418v1 Announce Type: new Abstract: AI tools are being increasingly adopted in policing in the UK and worldwide. Racial bias is a known and well-documented risk, yet representatives of aff
arXiv:2608.05707v1 Announce Type: new Abstract: Frame selection is essential for applying Large Multimodal Models (LMMs) to long videos due to severe frame redundancy and limited context windows. Sinc
arXiv:2608.05263v1 Announce Type: new Abstract: Multi-agent orchestration frameworks are moving from demos to production, yet benchmarks typically report task accuracy without diagnosing why a pipelin
arXiv:2608.05188v1 Announce Type: cross Abstract: Despite ever-increasing sophistication in language model (LM) pre- and post-training pipelines, many important failures persist: models overcondition
arXiv:2608.05326v1 Announce Type: cross Abstract: Autoregressive large language model inference is increasingly constrained by the memory footprint of the Key-Value (KV) cache. A dominant line of work
arXiv:2608.06310v1 Announce Type: cross Abstract: Recent advances in reward modeling show a paradigm shift from discriminative reward models to generative reward models. However, despite their strong
arXiv:2608.05627v1 Announce Type: new Abstract: Training-free open-vocabulary segmentation remains limited by a missing inference abstraction. Frozen vision-language features are produced at patch lev
arXiv:2608.05864v1 Announce Type: new Abstract: Large language models are increasingly applied as autonomous decision-making agents. However, in executive business decisions, existing benchmarks are l
arXiv:2506.18203v3 Announce Type: replace Abstract: Verifiers can improve language model capabilities by scoring and ranking responses from generated candidates. Currently, high-quality verifiers are
arXiv:2608.05587v1 Announce Type: new Abstract: Autonomous mobile GUI agents require accurate action reflection for reliable long-horizon execution. Existing approaches rely on open-ended multimodal r
arXiv:2608.06361v1 Announce Type: new Abstract: Real-world video benchmarks provide broad coverage, but their fixed clips entangle event count, rate, duration, and visual complexity, making failure mo
arXiv:2608.06065v1 Announce Type: new Abstract: GUI agents are commonly trained offline from successful interaction trajectories. Standard training decomposes each trajectory into prefix-action pairs:
arXiv:2608.06366v1 Announce Type: new Abstract: Electronic health record (EHR) feature engineering is a major bottleneck in clinical research and AI, accounting for 39-45% of data scientists' workload
arXiv:2608.05729v1 Announce Type: new Abstract: As capabilities rapidly increase, AI agents can move from running inside one app to acting across a user's devices over time. Yet existing agent systems
arXiv:2608.05207v1 Announce Type: new Abstract: Frozen pretrained forecasters often fail in structured, recurring ways that are costly to repair through fine-tuning. We study corrective feature discov