Knowledge catalogue
arXiv:2511.14282v2 Announce Type: replace-cross Abstract: Deep neural networks achieve outstanding performance across vision and language tasks, yet their large parameter counts limit deployment in re
arXiv:2602.04003v3 Announce Type: replace Abstract: Most adversarial threats in artificial intelligence (AI) target the computational behavior of models rather than the humans who rely on them. Yet mo
when evaluating long running agents, all of your evals don't need to be end to end. i'm working on a proper blog about this, but in our evals for our agents that run for 30-60 minutes, we have two set
arXiv:2510.06062v2 Announce Type: replace Abstract: Reinforcement learning (RL) has shown great promise in large language models (LLMs) post-training, which typically rely on token-level clipping to m
doomers and AI fans love hearing “it’s over” - but @scaling01 really should have noted that the below refers to a domain specific benchmark (exploitbench) rather than general purpose AI. also note the
symbolic tools like those listed below - rather than pure scaling -are likely driving most of the advances now. once you realize that you realize that hyperscaling is probably insane. @GaryMarcus IMHO
the whole point of databases is to keep reliable records of values that change over time. in general, they can be trusted to be stable over time. the whole point of LLMs is to raise money. in general
Setting a GPU power limit using nvidia-smi reduces heat output by approximately 20% with only a 5-8% inference speed loss. Undervolting the GPU can reduce power consumption by 5-15% with zero performa
A milestone for Pearl Research Labs: our first major enterprise partnership is live with Together AI. @togethercompute’s inference platform is an ideal demonstration of @prlnet's value proposition — O
arXiv:2605.13905v1 Announce Type: cross Abstract: Drug development and pharmacovigilance are frequently bottlenecked by legacy clinical reporting pipelines. These monolithic systems encode regulatory-
arXiv:2510.19973v4 Announce Type: replace-cross Abstract: The path to higher network autonomy in 6G lies beyond the mere optimization of key performance indicators (KPIs), requiring systems that perce
arXiv:2505.09246v4 Announce Type: replace-cross Abstract: In many real-world settings, machine learning models and interactive systems have access to both structured knowledge, e.g., knowledge graphs
b9172 is a release of llama.cpp that includes binaries for macOS, Linux, Android, Windows, and openEuler platforms with support for various hardware configurations including CPU, Vulkan, CUDA, ROCm, O
arXiv:2605.14054v1 Announce Type: new Abstract: Achieving robust perception-reasoning synergy is a central goal for advanced Vision-Language Models (VLMs). Recent advancements have pursued this goal v
arXiv:2605.14791v1 Announce Type: cross Abstract: Recent advances in artificial intelligence (AI) agents are pushing AI beyond tools toward autonomous scientific discovery. We discuss two complementar
arXiv:2605.14773v1 Announce Type: cross Abstract: Data selection accelerates training by identifying representative training data while preserving model performance. However, existing methods mainly f
Big move from arXiv: a one-year ban for authors who submit AI-generated content without proper checking. This is not about banning AI from academia. AI can be extremely useful. It can help us write be
arXiv:2602.20571v2 Announce Type: replace Abstract: Many benchmarks for automated causal inference evaluate a system's performance based on a single numerical output, such as an Average Treatment Effe
arXiv:2511.15408v2 Announce Type: replace-cross Abstract: Chinese demonstrates high semantic compactness and rich metaphorical expressiveness, enabling limited text to convey dense meanings while incr
arXiv:2605.14795v1 Announce Type: new Abstract: Referring Multi-Object Tracking (RMOT) faces a fundamental structural contradiction between the high-discriminability demand and the sparse semantic sup
arXiv:2605.14752v1 Announce Type: cross Abstract: Accurately identifying student misconceptions is crucial for personalized education but faces three challenges: (1) data scarcity with long-tail distr
arXiv:2506.08584v4 Announce Type: replace Abstract: Medical question answering (QA) benchmarks often focus on multiple-choice or fact-based tasks, leaving open-ended answers to real patient questions
arXiv:2605.14517v1 Announce Type: cross Abstract: Holistic evaluation scores capture overall output quality but do not distinguish whether a model reproduced the structural form of a user's request fr
arXiv:2605.14420v1 Announce Type: new Abstract: Current Large Language Models (LLMs) typically rely on coarse-grained national labels for pluralistic value alignment. However, such macro-level supervi
arXiv:2605.14842v1 Announce Type: new Abstract: Humans naturally communicate through abstract concepts like 'mood'. However, current image editing benchmarks focus primarily on explicit, literal comma
arXiv:2605.14995v1 Announce Type: new Abstract: Every day, users generate digital traces (e.g., social media posts, chats, and online interactions) that are inherently timestamped and may reflect aspe
arXiv:2602.03417v2 Announce Type: replace Abstract: Large language models hallucinate factual claims and struggle to ground their outputs in retrievable evidence, particularly in non-English languages
arXiv:2602.01664v4 Announce Type: replace Abstract: In recent years, agentic workflows have been widely applied to solve complex human tasks. However, existing workflow construction still faces key ch
arXiv:2511.05820v2 Announce Type: replace-cross Abstract: The rapid growth of Web APIs has made automated Web API recommendation essential for efficient mashup development. However, existing approache
Gary Marcus critiques the claim that token prediction in large language models constitutes genuine thought or reasoning, using the analogy of smartphone autocomplete to illustrate that predictive text
arXiv:2605.15018v1 Announce Type: cross Abstract: Shapley value and its priority-aware extensions are widely used for valuation in machine learning, but existing methods require pairwise priority to b
arXiv:2602.06718v2 Announce Type: replace-cross Abstract: Citations provide the basis for trusting scientific claims; when they are invalid or fabricated, this trust collapses. With the advent of Larg
arXiv:2605.14259v1 Announce Type: new Abstract: Applying Large Language Models (LLMs) to heterogeneous enterprise systems is hindered by hallucinations and failures in multi-hop, n-ary reasoning. Exis
arXiv:2605.14851v1 Announce Type: cross Abstract: Operational plan generation and verification are critical for modern complex and rapidly changing battlefield environments, yet traditional generation
arXiv:2512.12772v2 Announce Type: replace-cross Abstract: Understanding videos inherently requires reasoning over both visual and auditory information. To properly evaluate Omni-Large Language Models
arXiv:2605.14527v1 Announce Type: new Abstract: Developing machine learning interatomic potentials (MLIPs) for complex materials systems remains challenging because it requires expertise in atomistic
arXiv:2605.14301v1 Announce Type: new Abstract: Domain adaptation faces a fundamental paradox in the cold-start regime. When target data is scarce, statistical methods fail to distinguish relevant sou
arXiv:2605.14483v1 Announce Type: new Abstract: Large language models (LLMs) have become a strong foundation for multi-agent systems, but their effectiveness depends heavily on orchestration design. A
arXiv:2605.06132v2 Announce Type: replace Abstract: In agent memory systems, the reranking model serves as the critical bridge connecting user queries with long-term memory. Most systems adopt the 're
arXiv:2510.23477v2 Announce Type: replace Abstract: Effective math tutoring requires not only solving problems but also diagnosing students' difficulties and guiding them step by step. While multimoda
arXiv:2511.08565v3 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly operate in social contexts, motivating analysis of how they express and shift moral judgments. In th
arXiv:2605.14364v1 Announce Type: new Abstract: Continual learning requires models to adapt to new data while preserving previously acquired knowledge. At its core, this challenge can be viewed as pri
arXiv:2605.14635v1 Announce Type: cross Abstract: This paper introduces a multi-label visual emotion analysis benchmark dataset for comprehensively evaluating the ability of multimodal large language
arXiv:2603.29665v2 Announce Type: replace Abstract: Agentic systems for business process automation often require compliance with policies governing conditional updates to the system state. Evaluation
Ollama is an open-source framework that enables users to run large language models locally on their machines without requiring cloud services or significant computational resources. The project suppor
arXiv:2605.14055v1 Announce Type: cross Abstract: Parameter-Efficient Fine-Tuning (PEFT) is widely used for adapting Large Language Models (LLMs) for various tasks. Recently, there has been an increas
arXiv:2605.14040v1 Announce Type: new Abstract: We audit the multimodal-physics evaluation pipeline end-to-end and document three undetected construction practices that distort how the field measures
arXiv:2504.11703v3 Announce Type: replace-cross Abstract: AI agents interact with external environments through tool calls, exposing them to attacks like indirect prompt injection that can trigger una
arXiv:2605.14152v1 Announce Type: cross Abstract: Safety evaluations for large language models (LLMs) increasingly target high-stakes National Security and Public Safety (NSPS) risks, yet multilingual
arXiv:2605.15026v1 Announce Type: cross Abstract: Online OS tuning can improve long-running services, but existing controllers are poorly matched to live hosts. They treat scheduler, power, memory, an
arXiv:2510.00231v2 Announce Type: replace-cross Abstract: KV cache compression promises increased throughput and efficiency with negligible loss in performance. While the gains in throughput are indis
arXiv:2605.14177v1 Announce Type: cross Abstract: Long-horizon personalization requires dialogue assistants to retrieve user-specific facts from extended interaction histories. In practice, many relev
arXiv:2605.14717v1 Announce Type: cross Abstract: Label-free single-cell imaging offers a scalable, non-invasive alternative to fluorescence-based cytometry, yet inferring molecular phenotypes directl
arXiv:2605.13989v1 Announce Type: new Abstract: We present VectraYX-Nano, a 41.95M-parameter decoder-only language model trained from scratch in Spanish for cybersecurity, with a Latin-American focus
arXiv:2605.14710v1 Announce Type: cross Abstract: Deep learning and multi-modal fusion have demonstrated transformative potential in medical diagnosis by integrating diverse data sources. However, acc
We've gone even farther: Nemotron 3 Super is 120B and pretrained on 25T tokens in NVFP4. Nemotron 3 Ultra is ~500B and also pretrained in NVFP4. Accelerated computing means we rethink every aspect of
arXiv:2605.14257v1 Announce Type: new Abstract: We describe two types of models for vocabulary difficulty prediction: a high-accuracy black-box model, which achieved the top shared task result in the
Wow! What a week! Lots of new things to learn - new ideas to form The complete Agent Development Life Cycle 🎯 ❤️ SF but can’t wait to get home and back to building! Thanks for the warm welcome and fun
arXiv:2605.12532v1 Announce Type: cross Abstract: Conventional algorithmic trading systems are grounded in deterministic heuristics or offline-trained statistical models that cannot adapt to the seman
arXiv:2502.15761v3 Announce Type: replace-cross Abstract: The deployment of large language models (LLMs) on extended reality (XR) devices has great potential to advance the field of human-AI interacti