1071 papers
EasyAnimate is a high-performance video generation framework that leverages diffusion transformers enhanced by Hybrid Window Attention for improved efficiency, reward backpropagation for better quality alignment, and additional optimizations like token-length training and multimodal text encoding to achieve state-of-the-art results.
This paper addresses the theoretical and practical challenges of balancing similarity and diversity in dense vector retrieval by formally defining the NP-complete VRSD problem and proposing a novel parameter-free heuristic that outperforms existing methods like MMR and k-DPP.
This study demonstrates that Retrieval-Augmented Generation (RAG) significantly enhances the accuracy and transparency of pancreatic cancer staging in large language models by enabling them to retrieve and cite relevant clinical guidelines, outperforming both non-RAG versions of the same model and models provided with guidelines but lacking retrieval capabilities.
This paper introduces a Logic Augmented Generation (LAG) framework that combines semantic knowledge graphs with prompt heuristics to enhance multimodal analogical reasoning, demonstrating superior performance and explainability in metaphor detection tasks compared to existing baselines and human benchmarks, while also highlighting current limitations in domain-specific understanding.
This paper presents a semi-automated workflow using LLMs and knowledge graphs to quantify the scientific accuracy of climate change news, finding that while expert-validated tools offer beneficial veracity indications, current limitations in knowledge graph completeness and processing scale hinder widespread application.
This paper proposes MiCo, a hierarchical language agent framework that leverages large language models to design adaptive heuristics for solving the complex Online Dynamic Multidimensional Bin Packing problem in cloud VM scheduling, achieving a 96.9% competitive ratio in large-scale, real-world scenarios.
This paper introduces CausalPitfalls, a comprehensive benchmark designed to rigorously evaluate and expose the significant limitations of large language models in handling statistical causal inference pitfalls, such as Simpson's paradox, through both direct and code-assisted prompting protocols.
This paper introduces ShIOEnv, a grammar-constrained, self-supervised Bash environment that generates 2.1 million system-grounded input-output pairs to significantly improve the accuracy of modeling complex command-line execution behaviors compared to prior execution-free approaches.
The paper introduces SealQA, a new benchmark comprising three challenging flavors (Seal-0, Seal-Hard, and LongSeal) designed to evaluate search-augmented language models on fact-seeking tasks with noisy or conflicting web results, revealing that even frontier models struggle significantly with reasoning accuracy, robustness to noise, and long-context document retrieval.
This paper introduces LUCIFER, an inference-only middleware that decouples online language grounding from decision-making via a Signal Contract, enabling autonomous systems to robustly convert evolving human verbal reports into control-relevant signals that improve safety and information efficiency across diverse planning architectures.
This paper introduces EDINET-Bench, a challenging open-source benchmark derived from ten years of Japanese financial reports to evaluate LLMs on complex tasks like fraud detection and earnings forecasting, revealing that current models struggle significantly without specialized scaffolding and highlighting the need for more realistic evaluation frameworks.
This paper demonstrates that Reinforcement Fine-Tuning (RFT) outperforms Supervised Fine-Tuning (SFT) in preserving prior knowledge for multimodal large language models by leveraging training data with smaller influence magnitudes and better alignment to the base model's probability landscape, thereby mitigating catastrophic forgetting while enabling effective task adaptation.
The paper introduces La Leaderboard, the first open-source, community-driven initiative that evaluates 50 generative LLMs across 66 datasets covering Spanish varieties and the languages of Spain and Latin America to establish evaluation standards and promote linguistic diversity.
MuRating is a scalable framework that transfers high-quality English data-quality signals to a unified multilingual evaluator via pairwise comparisons and translation, enabling the selection of balanced, high-quality datasets that significantly improve the performance of multilingual large language models on both English and non-English benchmarks.
This paper introduces Eka-Eval, an open-source, modular evaluation framework designed to provide comprehensive, accessible, and reproducible benchmarking for low-resource multilingual large language models through a unified platform that integrates over 55 benchmarks and outperforms existing baselines in usability and efficiency.
This paper introduces TreeBench, a diagnostic benchmark for evaluating traceable visual grounded reasoning, and proposes TreeVGR, a reinforcement learning-based training paradigm that significantly enhances model performance by jointly supervising localization and reasoning.
Vevo2 is a unified framework for controllable speech and singing voice generation that employs novel audio tokenizers and a two-stage modeling approach with specialized training strategies to achieve flexible control over content, prosody, style, and timbre while demonstrating strong generalization across diverse synthesis tasks.
This study comprehensively evaluates how weight and activation quantization influences various forms of bias in large language models, revealing that while it can reduce toxicity and preserve sentiment, it often exacerbates stereotypes and unfairness in generative tasks, particularly under aggressive compression.
This paper proposes an unbalanced optimal transport-based alignment model that reframes acoustic-linguistic matching as a detection problem to effectively handle structural asymmetries and distributional mismatches, thereby improving knowledge transfer performance in CTC-based automatic speech recognition systems.
This paper proposes TSPC, a novel two-stage phoneme-centric architecture that leverages an extended Vietnamese phoneme set as an intermediate representation to significantly improve Vietnamese-English code-switching speech recognition accuracy while maintaining computational efficiency.