Knowledge catalogue
arXiv:2605.11679v2 Announce Type: replace Abstract: In the realm of multi-objective alignment for large language models, balancing disparate human preferences often manifests as a zero-sum conflict. S
arXiv:2602.22455v2 Announce Type: replace Abstract: We investigate the feasibility of using Multimodal Large Language Models (MLLMs) for real-time online episodic memory question answering. While clou
arXiv:2512.07112v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have demonstrated remarkable performance due to their large parameter counts and extensive training data. However
arXiv:2605.13321v1 Announce Type: new Abstract: VLN has achieved remarkable progress by scaling data and model capacity. However, the assumption of a static environment breaks down in real-world indoo
arXiv:2605.13424v1 Announce Type: new Abstract: We propose last-mile fine-tuning, or Lift, a pipeline in which a pre-trained large language model extracts an initial table from unstructured clipboard
arXiv:2605.13688v1 Announce Type: new Abstract: Medical segmentation foundation models such as SAM and MedSAM provide strong prompt-driven segmentation, but their image encoders are still too large fo
arXiv:2605.12703v1 Announce Type: cross Abstract: We introduce MMCL-Bench, a benchmark for multimodal context learning: learning task-local rules, procedures, and empirical patterns from visual or mix
arXiv:2605.13155v1 Announce Type: new Abstract: Text-to-image generation models have achieved remarkable progress in preference optimization, yet achieving robust alignment across diverse reward model
arXiv:2605.13370v1 Announce Type: new Abstract: For over a decade, explicit memory architectures like the Neural Turing Machine have remained theoretically appealing yet practically intractable for la
arXiv:2605.12803v1 Announce Type: new Abstract: Detecting concept drift in high-speed data streams remains challenging, particularly when models must operate on unlabeled data and avoid false alarms c
arXiv:2605.12869v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in a wide range of applications, yet remain vulnerable to adversarial jailbreak attacks that ci
arXiv:2510.13999v3 Announce Type: replace-cross Abstract: Sparsely-activated Mixture-of-Experts (SMoE) models offer efficient pre-training and low latency but their large parameter counts create signi
arXiv:2605.13047v1 Announce Type: cross Abstract: Evaluating whether large vision-language models (VLMs) align with human perception for high-level semantic scene comprehension remains a challenge. Tr
arXiv:2605.12872v1 Announce Type: new Abstract: Despite the recent success of Multimodal Foundation Models (FMs), their reliance on massive paired datasets limits their applicability in low-data and r
arXiv:2602.07458v4 Announce Type: replace Abstract: Online Reinforcement Learning (RL) offers a promising avenue for complex image editing but is currently constrained by the scarcity of reliable and
arXiv:2605.12763v1 Announce Type: new Abstract: Rich feature learning in tasks that unfold over time often requires the model to pass through bifurcations, constituting qualitative changes in the unde
arXiv:2605.12524v1 Announce Type: cross Abstract: We introduce ProofGrid, a benchmark suite for evaluating LLM reasoning through machine-checkable proofs rather than final answers alone. ProofGrid con
arXiv:2601.19667v2 Announce Type: replace-cross Abstract: We present SynCABEL (Synthetic Contextualized Augmentation for Biomedical Entity Linking), a framework that addresses a central bottleneck in
arXiv:2507.18553v4 Announce Type: replace Abstract: Quantizing the weights of large language models (LLMs) from 16-bit to lower bitwidth is the de facto approach to deploy massive transformers onto mo
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:2605.11033v1 Announce Type: cross Abstract: TokaMind is a multi-modal transformer (MMT) foundation model pre-trained on tokamak plasma diagnostics data from MAST, where it was shown to outperfor
arXiv:2605.13414v1 Announce Type: new Abstract: Deploying language models as autonomous agents requires more than per-task accuracy: when an agent faces a queue of problems under a finite token budget
arXiv:2605.13835v1 Announce Type: new Abstract: Class-Incremental Learning (CIL) enables models to continuously integrate new knowledge while mitigating catastrophic forgetting. Driven by the remarkab
arXiv:2605.13846v1 Announce Type: cross Abstract: This paper introduces WARDEN, an early language model system capable of transcribing and translating Wardaman, an endangered Australian indigenous lan
arXiv:2605.13674v1 Announce Type: cross Abstract: Weakly supervised semantic segmentation (WSSS) trains dense pixel-level segmentation models from partial or coarse annotations such as bounding boxes,
arXiv:2605.11581v1 Announce Type: new Abstract: When large language models (LLMs) serve real-time inference in commercial online advertising systems, end-to-end latency must be strictly bounded to the
arXiv:2605.12025v1 Announce Type: new Abstract: Neural operators provide a framework for learning solution operators of partial differential equations (PDEs), enabling efficient surrogate modeling for
arXiv:2412.05225v3 Announce Type: replace Abstract: Large Language Models (LLMs) based on transformers achieve cutting-edge results on a variety of applications. However, their enormous size and proce
arXiv:2605.12413v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) show strong visual perception, yet remain limited in reasoning about space under changing viewpoints. We study
arXiv:2602.00767v2 Announce Type: replace Abstract: Emergent misalignment can arise when a language model is fine-tuned on a narrowly scoped supervised objective: the model learns the target behavior,
arXiv:2605.12339v1 Announce Type: new Abstract: Aligning language models for both helpfulness and safety typically requires complex pipelines-separate reward and cost models, online reinforcement lear
arXiv:2605.11304v1 Announce Type: new Abstract: Chest radiograph interpretation requires temporal reasoning over prior and current studies, yet most vision-language models are trained on static image-
arXiv:2603.28488v2 Announce Type: replace Abstract: Large language models (LLMs) remain unreliable for high-stakes claim verification due to hallucinations and shallow reasoning. While retrieval-augme
arXiv:2605.12501v1 Announce Type: new Abstract: Computer-use agents (CUAs) automate on-screen work, as illustrated by GPT-5.4 and Claude. Yet their reliability on complex, low-frequency interactions i
arXiv:2605.11504v1 Announce Type: new Abstract: Recent advances in Large Language Models (LLMs) have enabled agentic systems for complex, multi-step tasks; cybersecurity is emerging as a prominent app
arXiv:2605.11109v1 Announce Type: cross Abstract: Self-supervised learning (SSL) has emerged as a promising approach to seismic data denoising as it does not require clean reference data. In this work
arXiv:2510.27055v2 Announce Type: replace Abstract: We present Contamination Detection via Context (CoDeC), a practical and accurate method to detect and quantify training data contamination in large
arXiv:2605.11601v1 Announce Type: new Abstract: Autoregressive language models are widely used for text evaluation, however, their left-to-right factorization introduces positional bias, i.e., early t
arXiv:2605.11005v1 Announce Type: new Abstract: Mixture-of-experts (MoE) architectures enable trillion-parameter LLMs with sparsely activated experts. Expert parallelism (EP) is a widely adopted MoE t
arXiv:2605.11019v1 Announce Type: new Abstract: Although large language models rely on chain-of-thought for complex reasoning, the overthinking phenomenon severely degrades inference efficiency. Exist
arXiv:2605.11607v1 Announce Type: cross Abstract: Probabilistic partial least squares (PPLS) is a central likelihood-based model for two-view learning when one needs both interpretable latent factors
arXiv:2605.11613v1 Announce Type: new Abstract: On-policy self-distillation has emerged as a promising paradigm for post-training language models, in which the model conditions on environment feedback
arXiv:2605.11541v1 Announce Type: new Abstract: Geoscience intelligence is expected to understand, reason about, and predict earth system changes to support human decision-making in critical domains s
arXiv:2605.12369v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models aim for general robot learning by aligning action as a modality within powerful Vision-Language Models (VLMs). Exist
arXiv:2601.20255v2 Announce Type: replace-cross Abstract: SWE-bench has emerged as the premier benchmark for evaluating Large Language Models on complex software engineering tasks. While these capabil
arXiv:2605.11663v1 Announce Type: new Abstract: Authentic school examinations provide a high-validity test bed for evaluating multimodal large language models (MLLMs), yet benchmarks grounded in Japan
arXiv:2505.13770v3 Announce Type: replace-cross Abstract: Reliable causal inference is essential for making decisions in high-stakes areas like medicine, economics, and public policy. However, it rema
arXiv:2605.12471v1 Announce Type: cross Abstract: We introduce KV-Fold, a simple, training-free long-context inference protocol that treats the key-value (KV) cache as the accumulator in a left fold o
arXiv:2605.12128v1 Announce Type: new Abstract: Large language models are increasingly deployed in safety-critical applications, where their ability to resist harmful instructions is essential. Althou
arXiv:2605.11396v1 Announce Type: new Abstract: The Muon optimizer has emerged as a compelling alternative to Adam for training large language models, achieving remarkable computational savings throug
arXiv:2605.11303v1 Announce Type: new Abstract: We investigate the use of Large Language Models (LLMs) for zero-shot prediction of Ryff Psychological Well-Being (PWB) scores from spontaneous speech. U
arXiv:2409.08290v4 Announce Type: replace-cross Abstract: Spiking Neural Networks (SNNs) promise higher energy efficiency over conventional Quantized Artificial Neural Networks (QNNs) due to their eve
arXiv:2605.11659v1 Announce Type: new Abstract: Cross-Domain Few-Shot Learning (CDFSL) aims to adapt large-scale pretrained models to specialized target domains with limited samples, yet the few-shot
arXiv:2605.11685v1 Announce Type: new Abstract: Large language model (LLM) unlearning aims to remove specific data influences from pre-trained model without costly retraining, addressing privacy, copy
arXiv:2605.12006v1 Announce Type: new Abstract: The performance of promptable video object segmentation (PVOS) models substantially degrades under input corruptions, which prevents PVOS deployment in
arXiv:2605.11800v1 Announce Type: cross Abstract: Large language models (LLMs) with mixture-of-experts (MoE) architectures achieve remarkable scalability by sparsely activating a subset of experts per
arXiv:2605.11689v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) architectures have become standard in large language models, yet many of their core design choices - expert count, granularit
arXiv:2605.11246v1 Announce Type: new Abstract: Offline black-box optimization aims to discover novel designs with high property scores using only a static dataset, a task fundamentally challenged by
arXiv:2412.14461v4 Announce Type: replace Abstract: Unstructured text data annotation is foundational to management research. LLMs offer a cost-effective and scalable alternative to human annotation,
arXiv:2605.12288v1 Announce Type: new Abstract: Direct Preference Optimization (DPO) is a widely used RL-free method for aligning language models from pairwise preferences, but it models preferences o