Knowledge catalogue
arXiv:2605.26678v1 Announce Type: new Abstract: Long-context language models are limited by the memory footprint of the key-value (KV) cache. Existing training-free KV compression methods usually rank
arXiv:2605.26584v1 Announce Type: new Abstract: Omnimodal large language models enable unified audio video understanding, but long joint token sequences make inference costly, and existing benchmarks
arXiv:2605.26399v1 Announce Type: new Abstract: Understanding human gaze behavior is essential for complex scene comprehension and human-computer interaction. Traditional gaze following models are typ
arXiv:2605.26840v1 Announce Type: new Abstract: Reinforcement learning with evaluation metrics as rewards is widely used to enhance specific capabilities of language models. However, for tasks such as
arXiv:2511.20586v4 Announce Type: replace Abstract: Trustworthiness has become a key requirement for the deployment of artificial intelligence systems in safety-critical applications. Conventional eva
arXiv:2602.17003v2 Announce Type: replace-cross Abstract: Large language models have advanced web agents, yet current agents lack personalization capabilities. Since users rarely specify every detail
arXiv:2605.27117v1 Announce Type: new Abstract: AI safety is still largely framed as alignment: training models to follow human preferences, safety policies, and normative constraints. That framing ha
arXiv:2602.00959v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) can be seen as compressed knowledge bases, but it remains unclear what knowledge they truly contain and how far t
arXiv:2512.04868v2 Announce Type: replace-cross Abstract: Knowledge-based conversational question answering (KBCQA) confronts persistent challenges in resolving coreference, modeling contextual depend
arXiv:2508.05305v2 Announce Type: replace Abstract: The recently proposed Large Concept Model (LCM) generates text by predicting a sequence of sentence-level embeddings and training with either mean-s
arXiv:2605.26898v1 Announce Type: cross Abstract: Large Language Models (LLMs) can generate functional source code from natural-language prompts, but often fail to consistently follow higher-level arc
arXiv:2508.07996v2 Announce Type: replace Abstract: Group Activity Detection (GAD) involves recognizing social groups and their collective behaviors in videos. Vision Foundation Models (VFMs), like DI
arXiv:2601.05899v2 Announce Type: replace Abstract: Recent breakthroughs in Large Language Models (LLMs) have positioned them as a promising paradigm for agents, with long-term planning and decision-m
arXiv:2605.26795v1 Announce Type: new Abstract: Chain-of-thought (CoT) prompting reliably improves language-model accuracy, but which properties of a rationale text drive the improvement is poorly und
arXiv:2605.26660v1 Announce Type: new Abstract: Quantization is an effective approach to reduce the memory footprint and inference cost of large language models (LLMs), yet maintaining performance in
arXiv:2605.25584v1 Announce Type: cross Abstract: Multi-robot task allocation usually assumes some combination of communication, known task models, or a coordinator. We study the opposite extreme, a r
arXiv:2605.23974v1 Announce Type: new Abstract: Current language models create two safety challenges: risk must be detected early enough to avoid exposing harmful continuation, and the harmfulness its
arXiv:2605.25707v1 Announce Type: new Abstract: Autonomous computer use agents that powered by multimodal large language models (MLLMs) are emerging as capable assistants for completing complex digita
arXiv:2605.24266v1 Announce Type: cross Abstract: Recent advances in large language models (LLMs) have enabled deep research systems that synthesize comprehensive, report-style answers to open-ended q
arXiv:2511.12046v2 Announce Type: replace-cross Abstract: Knowledge Distillation (KD) is essential for compressing large models, yet relying on pre-trained 'teacher' models downloaded from third-party
arXiv:2605.24219v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed as autonomous agents that reason, use tools, and act over multiple steps. Yet most hallucination
arXiv:2605.23913v1 Announce Type: cross Abstract: Cloud-hosted large language models (LLMs) commonly rely on LoRA for domain adaptation, yet domain data are distributed across multiple edge devices an
arXiv:2510.26418v4 Announce Type: replace Abstract: Large Reasoning Models (LRMs) improve task performance through extended inference-time reasoning. Although previous studies suggest that longer reas
arXiv:2605.24305v1 Announce Type: cross Abstract: Standard accuracy on binary reasoning benchmarks hides critical failure modes: prior collapse, inconsistency under paraphrase, and inability to reason
arXiv:2605.26086v1 Announce Type: new Abstract: Large language model agents are increasingly envisioned as always-on personal assistants with access to anything relevant in the user's digital world. Y
arXiv:2604.18179v2 Announce Type: replace-cross Abstract: Hosted-LLM providers have a silent-substitution incentive: advertise a stronger model while serving cheaper replies. Probe-after-return scheme
arXiv:2605.25835v1 Announce Type: cross Abstract: This paper examines the specialization of Small Language Models (SLMs) with up to 4 billion parameters for generating artifacts in domain-specific lan
arXiv:2605.25962v1 Announce Type: cross Abstract: Machine unlearning removes designated concepts or knowledge from pre-trained models. Recent work has extended this paradigm to speaker identity unlear
arXiv:2602.04360v2 Announce Type: replace-cross Abstract: Hypergraph neural networks (HGNNs) effectively model higher-order interactions in many real-world systems but remain difficult to interpret, l
arXiv:2605.25603v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning improves the problem-solving ability of large language models (LLMs), but generated reasoning traces may not faithfully
arXiv:2605.06415v2 Announce Type: replace-cross Abstract: We introduce E = T*H/(O+B), a dimensionless control parameter that predicts whether Mixture-of-Experts (MoE) models will develop a healthy exp
arXiv:2502.10311v3 Announce Type: replace-cross Abstract: Most commonly used non-linear machine learning methods are closed-box models, uninterpretable to humans. The field of explainable artificial i
arXiv:2605.25645v1 Announce Type: cross Abstract: We present the first end-to-end demonstration of fine-tuning and serving Google's Gemma 4 31B model on TPU hardware, providing an empirical comparison
arXiv:2510.01384v4 Announce Type: replace Abstract: A natural desideratum for generative models is self-correction--detecting and revising low-quality tokens at inference. While Masked Diffusion Model
arXiv:2306.02216v3 Announce Type: replace Abstract: Federated Learning (FL) enables collaborative model training across distributed clients while preserving user privacy. Recently, Federated Unlearnin
arXiv:2605.24316v1 Announce Type: new Abstract: Scaling laws provide compact descriptions of how prediction error varies with compute, model size, and data, but existing theory mainly treats single-sa
arXiv:2605.24636v1 Announce Type: new Abstract: While large language models (LLMs) hold transformative potential for medicine, their reasoning robustness and safety in real-world clinical scenarios re
arXiv:2605.24518v1 Announce Type: cross Abstract: The quadratic complexity of self-attention in Transformer models remains a significant bottleneck for processing long sequences and deploying large la
arXiv:2503.07482v2 Announce Type: replace-cross Abstract: Membership Inference Attacks (MIAs) aim to estimate whether a specific data point was used in the training of a given model. Existing state-of
arXiv:2605.25475v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly expected to operate over long contexts, yet standard softmax attention incurs a KV cache that grows line
arXiv:2602.04653v4 Announce Type: replace-cross Abstract: Open-weight language models are increasingly used in production settings, raising new security challenges. One prominent threat is backdoor at
arXiv:2605.25244v1 Announce Type: new Abstract: Inference time optimization techniques, such as repeated sampling, have significantly advanced the reasoning capabilities of Large Language Models (LLMs
arXiv:2605.25415v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used in academic peer review, yet their reliability, alignment with human judgment, and robustness to adve
arXiv:2605.24417v1 Announce Type: new Abstract: Supervised classification for tabular data remains a core machine learning task, yet its reliance on large labeled datasets limits applicability in data
arXiv:2605.25030v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) systems offer a promising approach to reduce hallucinations and improve answer accuracy in large language models (L
arXiv:2605.25590v1 Announce Type: cross Abstract: We study nonstationary generalized linear bandits (GLBs), where the expected reward is modeled through a nonlinear link function with an unknown time-
arXiv:2605.26092v1 Announce Type: cross Abstract: The deployment of Large Language Models (LLMs) and Vision Transformers (ViTs) on edge devices is significantly constrained by memory limitations and t
arXiv:2602.00511v2 Announce Type: replace Abstract: Despite their empirical success, neural network classifiers remain difficult to interpret. In softmax-based models, class regions are defined implic
arXiv:2605.25572v1 Announce Type: cross Abstract: The growing complexity of quantum programming frameworks has exposed a critical limitation in existing large language model (LLM)-based code assistant
Nous Research has added support for Qwen 3.7 Max, a large language model, within their Hermes Agent framework. This integration enables users to leverage Qwen 3.7 Max's capabilities when building or d
arXiv:2602.02495v3 Announce Type: replace-cross Abstract: Direct alignment methods are increasingly used to align large language models (LLMs) with human preferences. However, many real-world alignmen
arXiv:2605.25984v1 Announce Type: cross Abstract: Ensuring safe and contextually appropriate behaviour in Large Language Models (LLMs) remains a critical challenge for real-world deployment. We presen
arXiv:2605.24541v1 Announce Type: cross Abstract: Text compression for large language model (LLM) systems is usually framed as token deletion, retrieval, summarization, or exact reconstruction. We stu
arXiv:2601.23164v2 Announce Type: replace Abstract: We study the stochastic linear bandits with parameter noise model, in which the reward of action a is a^op heta where heta is sampled i.i.d. We show
arXiv:2605.25162v1 Announce Type: cross Abstract: Large language models for vertical domains are bottlenecked by the scarcity of complex, domain-specific task-oriented dialogues. Existing data acquisi
arXiv:2605.25758v1 Announce Type: new Abstract: Large Language Models (LLMs) have reshaped user profiling, yet current evaluations mainly focus on static data snapshots. This paradigm overlooks the re
arXiv:2605.24782v1 Announce Type: new Abstract: While Vision Foundation Models (VFMs) excel at predictive tasks on satellite imagery, their performance can arise from visual correlations rather than u
arXiv:2605.25850v1 Announce Type: cross Abstract: This paper investigates large language model (LLM) abstention learning, specifically using ternary reward, which incentivize truthfulness in large lan
arXiv:2605.25541v1 Announce Type: cross Abstract: Neural networks encode inputs as high-dimensional vectors, known as representations, that capture how models process data by encoding task-relevant st
arXiv:2605.24213v1 Announce Type: cross Abstract: Evaluation harnesses are software systems that orchestrate model evaluation by managing model invocation, data loading, metric computation, and result