Knowledge catalogue
arXiv:2605.20641v1 Announce Type: cross Abstract: Inference optimization is a vital technique for deploying LLMs at scale. Compilation is the most widely adopted optimization technique for LLMs. While
arXiv:2505.19075v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have demonstrated remarkable general capabilities, but enhancing skills such as reasoning often demands substanti
arXiv:2605.19285v1 Announce Type: cross Abstract: The rapid spread of misinformation on social media platforms has become a formidable challenge. To mitigate its proliferation, Misinformation Detectio
arXiv:2605.18781v1 Announce Type: cross Abstract: Can LLMs simulate how humans form and change beliefs in social networks? We put this to the test by replicating an established study on belief dynamic
arXiv:2605.18868v1 Announce Type: cross Abstract: While vision and multimodal foundation models underpin critical tasks from perception to complex reasoning, they remain highly vulnerable to adversari
arXiv:2605.18932v1 Announce Type: cross Abstract: In this work, we propose HypergraphFormer, a novel and efficient approach to floor plan generation based on learning hypergraph representations with a
June 2024: The latest general-purpose LLMs could not count the r's in strawberry. July 2025: The latest general-purpose LLMs get gold in the International Math Olympiad. May 2026: The latest general-p
arXiv:2605.20072v1 Announce Type: new Abstract: Large Language Models are increasingly proposed as cognitive components for robotic systems, yet their opaque decision processes make it difficult to ex
arXiv:2605.18852v1 Announce Type: cross Abstract: Checkpoint selection for multimodal large language models (MLLMs) presents significant challenges when performance differentials are marginal and eval
arXiv:2602.09805v2 Announce Type: replace-cross Abstract: As reasoning LLMs increasingly trade tokens for accuracy through deliberation, search, and self-correction, a single accuracy score can no lon
arXiv:2510.01782v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) should refuse to answer questions beyond their knowledge. This capability, which we term knowledge-aware refusal,
arXiv:2601.11956v2 Announce Type: replace-cross Abstract: Reliable reasoning in Large Language Models (LLMs) is challenged by their propensity for hallucination. While augmenting LLMs with Knowledge G
arXiv:2603.11689v2 Announce Type: replace Abstract: Frontier Multimodal Large Language Models (MLLMs) exhibit remarkable capabilities in Visual-Language Comprehension (VLC) tasks. However, they are of
A developer created a terminal user interface (TUI) tool that enables local large language models (LLMs) running on Ollama or cloud platforms to debate each other as a method for detecting and reducin
arXiv:2605.16284v1 Announce Type: cross Abstract: Student use of Generative AI (GenAI) products in completing their classwork, with or without their professors' knowledge and/or approval, has resulted
arXiv:2605.17152v1 Announce Type: new Abstract: Multimodal LLMs are evolving from vision-language to tri-modality that see, hear, and read, yet pipelines and benchmarks remain English-centric and comp
arXiv:2605.17503v1 Announce Type: new Abstract: The decoding of linguistic information from electroencephalography (EEG) signals remains an extremely challenging problem in brain-computer interface (B
arXiv:2605.17967v1 Announce Type: new Abstract: This paper explores a scientific question in supervised fine-tuning (SFT): why SFT is broadly effective for small-scale deep neural networks, yet can pr
arXiv:2502.16691v2 Announce Type: replace Abstract: Recent research has increasingly focused on training large language models (LLMs) using federated learning, known as FedLLM. However, responsible AI
arXiv:2605.16686v1 Announce Type: new Abstract: Knowledge editing (KE) provides a lightweight alternative to repeated fine-tuning of LLMs. However, most existing KE methods target dense feed-forward l
arXiv:2605.18630v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed as scientific AI as- sistants, and a growing body of benchmarks evaluates their capabilities acro
arXiv:2605.17775v1 Announce Type: cross Abstract: Large language models (LLMs) can generate or synthesize clinical text for a wide range of applications, from improving clinical documentation to augme
I put together these annotated slides from my five minute lightning talk at PyCon US 2026, using the latest iteration of my annotated presentation tool. # I presented this lightning talk at PyCon US 2
arXiv:2605.15565v1 Announce Type: cross Abstract: Reinforcement learning (RL) is increasingly used to improve the reasoning, coding, and tool-use capabilities of large language models, but agentic RL
arXiv:2601.21798v2 Announce Type: replace Abstract: Large Language Models(LLMs) have revolutionized text generation and multimodal perception,but their capabilities in 3D content generation remain und
arXiv:2605.15417v1 Announce Type: cross Abstract: In GFlowNets and variational inference, it has been shown that the mean square error between target and model log probabilities is an effective, low v
arXiv:2605.15491v1 Announce Type: cross Abstract: Layer pruning removes entire Transformer decoder blocks from large language models, but introduces a mismatch between the hidden state received by the
Note that as of last summer Waymo said that LLMs/VLMs were experimental, and that their foundation model then could “process only a small amount of image frames, does not incorporate accurate 3D sensi
arXiv:2605.16117v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated strong capabilities across diverse NLP applications, such as translation, text generation, and question a
arXiv:2605.15613v1 Announce Type: new Abstract: Through an analysis of sequences generated by open-weight large language models (LLMs), we demonstrate that LLMs are heavily biased toward English. Whil
arXiv:2605.14117v1 Announce Type: cross Abstract: An AI system for professional floor plan design must precisely control room dimensions and areas while respecting the desired connectivity between roo
arXiv:2605.14458v1 Announce Type: new Abstract: Omni-modal large language models have demonstrated remarkable potential in holistic multimodal understanding; however, the token explosion caused by hig
arXiv:2605.14443v1 Announce Type: new Abstract: The shift toward interacting with frozen, 'black-box' Large Language Models (LLMs) has transformed prompt engineering from a heuristic exercise into a c
arXiv:2605.15000v1 Announce Type: cross Abstract: Premature closure, or committing to a conclusion before sufficient information is available, is a recognized contributor to diagnostic error but remai
This post discusses how traditional caching mechanisms assume deterministic behavior (identical inputs producing identical outputs), an assumption that breaks down with large language models and espec
arXiv:2512.10931v3 Announce Type: replace Abstract: Many state-of-the-art LLMs are trained to think before giving their answer. Reasoning can greatly improve language model capabilities, but it also m
arXiv:2605.12968v1 Announce Type: cross Abstract: Do large language models internally encode ontological relations in a formally verifiable algebraic structure? We introduce Algebraic Ontology Project
arXiv:2605.12772v1 Announce Type: new Abstract: Wu et al. (2026) showed that most frontier large language models (LLMs) recommend a sponsored, roughly twice-as-expensive flight when their system promp
arXiv:2605.12714v1 Announce Type: new Abstract: Hidden states change substantially across the layers of modern language models, but most layer-wise analyses focus on one aspect of that change. We prop
arXiv:2601.13359v2 Announce Type: replace-cross Abstract: Prefill attacks are an effective and low-cost jailbreaking method, as they directly insert an acceptance sequence (e.g., 'Sure, here is how to
Sebastian Raschka shared an HTML-formatted table comparing active parameter ratios across different large language model architectures for improved readability and to avoid text truncation. The resour
arXiv:2605.12978v1 Announce Type: new Abstract: Learning from past experience benefits from two complementary forms of memory: episodic traces -- raw trajectories of what happened -- and consolidated
1/ Excited to report we have a new paper out @Nature today! The bottom line: training data for LLMs does not just fall from the sky - it is created in the context of existing social political institut
arXiv:2605.11857v1 Announce Type: new Abstract: Federated fine-tuning of large language models is commonly formulated as a parameter aggregation problem. However, even parameter-efficient methods requ
arXiv:2601.03627v3 Announce Type: replace Abstract: We introduce EPAG, a benchmark dataset and framework designed for Evaluating the Pre-consultation Ability of LLMs using diagnostic Guidelines. LLMs
arXiv:2605.11706v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to complete complex tasks by selecting and coordinating external tools across multiple steps. This re
arXiv:2605.11195v1 Announce Type: new Abstract: Large language models (LLMs) trained on web-scale corpora can memorize sensitive training data, posing significant privacy risks. Differential privacy (
arXiv:2605.12242v1 Announce Type: new Abstract: Automatic Speech Recognition (ASR) transcripts often contain disfluencies, such as fillers, repetitions, and false starts, which reduce readability and
arXiv:2510.25356v2 Announce Type: replace Abstract: In the U.S. judicial system, a widespread approach to legal interpretation entails assessing how a legal text would be understood by an `ordinary' s
arXiv:2504.12326v3 Announce Type: replace Abstract: Clinical case reports and discharge summaries may be the most complete and accurate summarization of patient encounters, yet they are finalized, i.e
arXiv:2605.10876v1 Announce Type: cross Abstract: Recent advances in machine learning and large-scale biological data collections have revived the prospect of building a virtual cell, a computational
arXiv:2605.10793v1 Announce Type: new Abstract: Large language models (LLMs) are costly to deploy due to their large memory footprint and high inference cost. Weight-activation quantization can reduce
arXiv:2605.09803v1 Announce Type: cross Abstract: This research paper addresses the limitations of current mobile accessibility services like TalkBack, which provide manual gesture-based sequential fe
arXiv:2605.10633v1 Announce Type: cross Abstract: Fine-tuning Large Language Models (LLMs) on benign narrow data can sometimes induce broad harmful behaviors, a vulnerability termed emergent misalignm
'It is categorically *not* a victory for pure LLMs; it’s a victory for borrowing from classical AI and CS to move *beyond* pure LLMs.' ☝️ Compound AI Systems alllll the way downnn 🤩🤯🤩 Claude Code (sti
arXiv:2605.10401v1 Announce Type: new Abstract: Efficient branching policies are essential for accelerating Mixed Integer Linear Programming (MILP) solvers. Their design has long relied on hand-crafte
arXiv:2605.10807v1 Announce Type: cross Abstract: The integration of Large Language Models (LLMs) into Electronic Design Automation (EDA) and hardware security is rapidly reshaping the semiconductor i
arXiv:2605.08437v1 Announce Type: cross Abstract: Existing benchmarks for legal AI focus primarily on tasks where LLMs must produce legal arguments or documents, yet the capacity to judge such argumen
arXiv:2605.09365v1 Announce Type: new Abstract: Enterprise workloads are dominated by deterministic, structured, and knowledge-dependent tasks operating under strict cost, latency, and reliability con
arXiv:2605.10611v1 Announce Type: cross Abstract: This paper proposes a jailbreaking prompt detection method for large language models (LLMs) to defend against jailbreak attacks. Although recent LLMs