Knowledge catalogue
arXiv:2601.21698v2 Announce Type: replace-cross Abstract: Curriculum learning changes the order of pretraining data, but it remains unclear how ordering changes the learning dynamics. We pretrain mode
arXiv:2605.08614v1 Announce Type: new Abstract: Monitoring complex industrial assets relies on engineer-authored symbolic rules that trigger based on sensor conditions and prompt technicians to perfor
arXiv:2605.08568v1 Announce Type: new Abstract: Large language models (LLMs) have rapidly grown in scale, creating substantial memory and computational costs that hinder efficient deployment. Singular
arXiv:2603.04415v2 Announce Type: replace Abstract: Reasoning post-training improves Large Language Models (LLMs) on complex tasks such as mathematics and coding, but its benefits across diverse multi
arXiv:2601.20251v3 Announce Type: replace-cross Abstract: Exhaustively evaluating many large language models (LLMs) on a large suite of benchmarks is expensive. We cast benchmarking as finite-populati
arXiv:2506.11578v4 Announce Type: replace Abstract: Recently, large language models (LLMs) have demonstrated strong performance, ranging from simple to complex tasks. However, while large models achie
arXiv:2605.09370v1 Announce Type: cross Abstract: Large-scale AI training is now fundamentally a distributed systems problem, and hardware failures have become routine operating conditions rather than
arXiv:2605.09027v1 Announce Type: new Abstract: In multi-agent systems (MAS), a single deceptive agent can nullify all gains of an agentic AI collective and evade deployed defenses. However, existing
arXiv:2503.12333v2 Announce Type: replace Abstract: Safe, agile, and socially compliant multi-robot navigation in cluttered and constrained environments remains a critical challenge. This is especiall
arXiv:2602.06527v2 Announce Type: replace Abstract: Scaling test-time compute with multi-path chain-of-thought improves reasoning accuracy, but its effectiveness depends critically on the exploration-
arXiv:2605.08247v1 Announce Type: cross Abstract: GCC and LLVM underpin much of modern software infrastructure, relying on distinct Intermediate Representations (IRs) to drive optimizations and code g
arXiv:2605.09176v1 Announce Type: cross Abstract: Training large language models requires optimization algorithms that are not only statistically effective, but also computationally and memory efficie
arXiv:2605.10639v1 Announce Type: new Abstract: The rapid adoption of LLMs in both research and industry highlights the challenges of deploying them safely and reveals a gap in the systematic evaluati
arXiv:2605.09490v1 Announce Type: new Abstract: Reasoning LLMs produce thousands of chain-of-thought tokens whose KV cache must reside in scarce GPU HBM. The dominant response -- permanently evicting
arXiv:2605.08904v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities in reasoning and tool use. However, the fundamental cognitive faculties essential
arXiv:2605.08876v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed as autonomous agents that execute tool-augmented, multi-step tasks, where latency is a critical f
arXiv:2512.11470v2 Announce Type: replace-cross Abstract: Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) dominate the post-training landscape for mathematical reasoning, yet differ funda
arXiv:2605.06241v2 Announce Type: replace Abstract: Reinforcement learning has become the standard for improving reasoning in large language models, yet evidence increasingly suggests that RL does not
arXiv:2605.08313v1 Announce Type: cross Abstract: Large language models (LLMs) rely on deterministic pseudorandom number generators (PRNGs) for autoregressive sampling, creating a critical supply-chai
arXiv:2603.26089v2 Announce Type: replace-cross Abstract: The ability to represent oneself and others as agents with knowledge, intentions, and belief states that guide their behavior - Theory of Mind
arXiv:2605.10831v1 Announce Type: cross Abstract: Large language models possess strong chemical reasoning capabilities, making them effective molecular editors. However, property-relevant information
arXiv:2605.08220v1 Announce Type: new Abstract: The automated extraction of data from scientific charts is a critical task for large-scale literature analysis. While multimodal Large Language Models (
arXiv:2605.09618v1 Announce Type: new Abstract: When should a language model answer directly, sample and vote, or engage in multi-agent debate? Recent work shows voting often explains much of the gain
arXiv:2605.09536v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) offer a promising paradigm for parallel text generation, but in practice they face an accuracy-parallelism tra
arXiv:2605.09195v1 Announce Type: new Abstract: Large language models confidently produce outdated answers, and no existing method can detect them. We show this is not an engineering failure but a str
arXiv:2605.09739v1 Announce Type: cross Abstract: Large Language Models are increasingly used as zero-shot classifiers in complex reasoning tasks. However, standard constrained decoding suffers from a
arXiv:2605.10211v1 Announce Type: cross Abstract: Government transparency laws, like the Freedom of Information (FOIA) acts in the United States and United Kingdom, and the Woo (Open Government Act) i
arXiv:2605.08541v1 Announce Type: new Abstract: Neural scaling laws approximate a language model's loss as a power-law function of parameter count N and token count D. Following Chinchilla-style compu
Uncensored LLMs are architectures that have been modified or fine-tuned to remove standard safety alignment layers (guardrails) that limit a model's ability to discuss sensitive topics. Ollama offers
arXiv:2602.09789v3 Announce Type: replace Abstract: Scaling up model parameters has long been a prevalent training paradigm driven by the assumption that larger models yield superior generation capabi
arXiv:2605.07137v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has become a highly effective method for improving the reasoning abilities of Large Language Mod
With 32GB of RAM, 30B Q4 models run comfortably on M5 MacBook Air , and popular choices include Qwen 3.6 27B (requiring 18GB+ VRAM) and Qwen 3.6 9B (lightweight, runs on 8GB) . Ollama's macOS implemen
arXiv:2605.07111v1 Announce Type: cross Abstract: Recent literature on fine-tuning Large Language Models highlights a fundamental debate. While Full Fine-Tuning (FFT) provides the representational pla
arXiv:2605.07830v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as autonomous agents in offensive cybersecurity. In this paper, we reveal an interesting phenom
arXiv:2506.11512v2 Announce Type: replace-cross Abstract: Recently, Large Language Models (LLMs) have introduced a novel paradigm in Time Series Analysis (TSA), leveraging strong language capabilities
arXiv:2605.07925v1 Announce Type: new Abstract: Conversational Large Language Models are post-trained on language that expresses specific behavioural traits, such as curiosity, open-mindedness, and em
arXiv:2605.06676v1 Announce Type: cross Abstract: Long-context inference in Large Language Models (LLMs) is bottlenecked by the linear growth of Key-Value (KV) cache memory. Existing KV cache compress
arXiv:2605.06839v1 Announce Type: cross Abstract: Autonomous experimentation has transformed microscopy and materials discovery by enabling closed-loop optimization including imaging and spectroscopy
arXiv:2605.07850v1 Announce Type: cross Abstract: With the rise in scale for deep learning models to billions of parameters, the computational cost of fine-tuning remains a significant barrier to depl
arXiv:2605.07058v1 Announce Type: cross Abstract: Real-world clinical diagnosis is a complex process in which the doctor is required to obtain information from both interaction with the patient and co
arXiv:2603.09652v3 Announce Type: replace Abstract: With the rapid advancement of Large Language Models (LLMs) in code generation, human-AI interaction is evolving from static text responses to dynami
arXiv:2605.07363v1 Announce Type: cross Abstract: DeepSeek Sparse Attention (DSA) sets the state of the art for fine-grained inference-time sparse attention by introducing a learned token-wise indexer
arXiv:2605.07775v1 Announce Type: cross Abstract: Balancing exploration and exploitation is a core challenge in sequential decision-making and black-box optimization. We introduce POETS (extbf{Po}licy
arXiv:2605.07234v1 Announce Type: cross Abstract: Large language models (LLMs) support long-context inference but suffer from substantial memory and runtime overhead due to Key-Value (KV) Cache growth
arXiv:2605.06730v1 Announce Type: new Abstract: We introduce Semantic State Abstraction Interfaces (SSAI): a methodological template for mapping sparse unstructured text into K auditable, named coordi
arXiv:2605.08060v1 Announce Type: cross Abstract: Context window expansion is often treated as a straightforward capability upgrade for LLMs, but we find it systematically fails in multi-agent social
arXiv:2602.10693v3 Announce Type: replace-cross Abstract: Off-policy updates are inevitable in reinforcement learning (RL) for large language models (LLMs) due to rollout staleness from asynchronous t
arXiv:2602.01752v2 Announce Type: replace Abstract: As large language models (LLMs) generate increasingly human-like text, watermarking has emerged as a promising solution for reliable attribution bey
arXiv:2605.04066v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) is an essential paradigm that enhances the reasoning capabilities of Large Language Models (LLMs).
arXiv:2605.04236v1 Announce Type: new Abstract: Large Language Model ensembles improve reasoning accuracy up to a performance boundary; beyond it, additional deliberation degrades accuracy. Static-bud
arXiv:2505.00020v2 Announce Type: replace Abstract: Using a legally obtained dataset of 34 copyrighted O'Reilly Media books, we apply the DE-COP membership inference attack method to investigate wheth
arXiv:2603.08022v2 Announce Type: replace Abstract: A data mixture refers to how different data sources are combined to train large language models, and selecting an effective mixture is crucial for o
arXiv:2605.05097v1 Announce Type: cross Abstract: LLMs are trained once, then deployed into a world that never stops changing. External memory compensates for this, but most systems manage it explicit
arXiv:2605.04157v1 Announce Type: new Abstract: SemEval-2026 Task 13 investigates machine-generated code detection across multiple programming languages and application scenarios, asking participating
arXiv:2605.04572v1 Announce Type: cross Abstract: Safety alignment of Large Language Models (LLMs) is extremely fragile, as fine-tuning on a small number of benign samples can erase safety behaviors l
arXiv:2605.04738v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities. However, their massive parameter scale leads to significant resource consumption
arXiv:2605.04523v1 Announce Type: new Abstract: We present our winning system for Task~B (generation with reference passages) in SemEval-2026 Task~8: MTRAGEval. Our method is a heterogeneous ensemble
arXiv:2605.04468v1 Announce Type: cross Abstract: Post-training large language models (LLMs) often suffers from catastrophic forgetting, where improvements on a target objective degrade previously acq
arXiv:2605.05080v1 Announce Type: new Abstract: We administer 45 validated psychometric questionnaires to 50 large language models (LLMs) to identify the dimensions along which LLMs differ psychometri
arXiv:2605.04107v1 Announce Type: cross Abstract: Production agent frameworks (OpenAI Function Calling, Anthropic Tool Use, MCP) transmit tool schemas as JSON, a format designed for machine parsing, n