6486 papers
This paper proposes a novel method that leverages Large Language Models to evolve interpretable control policies represented as standard Python programs, offering a transparent and verifiable alternative to black-box neural network controllers for dynamical systems.
The paper introduces EoRA, a fine-tuning-free method that utilizes eigenspace low-rank approximation and an optimized CUDA kernel to significantly recover the accuracy of compressed LLMs while offering flexible trade-offs between performance and computational overhead.
This paper proposes a generic token cleaning pipeline for supervised fine-tuning of large language models that filters out uninformative tokens based on their influence on model updates, thereby improving downstream performance by prioritizing data quality over quantity at the token level.
This paper proposes DIFU-Ada, a training-free inference time adaptation framework that enables diffusion-based neural combinatorial solvers to achieve zero-shot cross-problem and cross-scale generalization without additional training, as demonstrated by a TSP-trained model successfully solving variants like PCTSP and OP.
This paper proposes a methodology that enables natural language interaction with Piping and Instrumentation Diagrams (P&IDs) by converting DEXPI data into labeled property graphs and integrating them with Large Language Models via graph-based retrieval augmented generation to enhance data retrieval, reduce hallucinations, and support engineering tasks.
This paper introduces SCAM, the largest and most diverse real-world dataset of typographic attack images, to evaluate and demonstrate the significant vulnerability of state-of-the-art multimodal foundation models to such attacks while providing empirical insights into how model architecture and training data influence robustness.
This paper proposes a novel data-driven framework using offline reinforcement learning and survival analysis to estimate optimal pricing and inventory control policies in sequential environments with censored and dependent demand, overcoming challenges like missing profit information and non-stationarity by approximating the problem as a high-order Markov decision process.
The paper proposes SwitchMT, a novel methodology for scalable multi-task learning in resource-constrained autonomous agents that combines a Deep Spiking Q-Network with active dendrites and an adaptive task-switching policy to effectively mitigate task interference and outperform state-of-the-art methods in Atari games.
This systematic review introduces the emerging interdisciplinary field of LLM Psychometrics, which applies psychometric theories and instruments to develop comprehensive evaluation frameworks for measuring human-like psychological constructs in large language models, ultimately guiding the creation of more robust, human-centered AI systems.
This paper introduces REI-Bench, the first benchmark for evaluating robot task planning under vague referring expressions, revealing that such vagueness significantly degrades performance and demonstrating that a task-oriented context cognition approach effectively mitigates this issue to improve accessibility for non-expert users.
This paper proposes a training-time approach that fine-tunes Large Language Models using instruction-tuning data augmented with pseudo-code representations of natural language instructions, resulting in significant improvements in instruction-following reliability and overall reasoning performance across multiple benchmarks.
This paper presents a data-driven survey of 14,648 studies from 2022 to early 2025, revealing that research on the limitations of large language models (LLLMs) has surged to over 30% of all LLM-related work, with reasoning, generalization, and hallucination being the most prominent areas of focus.
This paper proposes a consistency-based abductive reasoning framework that integrates predictions from multiple pre-trained models at test time to mitigate performance degradation in novel environments, achieving significant improvements in accuracy and F1-score over individual models and standard ensembles by selecting a subset of predictions that maximizes coverage while minimizing logical inconsistencies.
This study demonstrates that for retail sales forecasting characterized by intermittent demand and missing data, localized tree-based ensemble methods like XGBoost outperform sophisticated deep learning architectures, suggesting that aligning model selection with specific problem constraints is more critical than architectural complexity.
This paper proposes SILVR, a self-improving framework that enables visual robotic planners to iteratively enhance their performance on novel tasks by continuously updating an in-domain video model using self-collected trajectories, achieving robust results without requiring ground-truth reward functions or expert demonstrations.
The paper introduces ReLIFT, a novel training framework that interleaves reinforcement learning with online supervised fine-tuning on challenging questions, enabling large language models to acquire new knowledge and reasoning patterns beyond their original capabilities while achieving superior performance with significantly less demonstration data.
This survey provides a comprehensive overview of differential privacy in machine learning, tracing its theoretical evolution from symbolic AI to large language models, examining integration methods for privacy-preserving training, and outlining practical evaluation techniques.
This paper introduces Locality-aware Parallel Decoding (LPD), a novel framework combining flexible parallelized autoregressive modeling and locality-aware generation ordering to significantly accelerate autoregressive image generation by reducing inference steps and latency while maintaining high-quality results.
This paper argues that the interaction between human cognitive biases and AI chatbot behaviors like sycophancy creates dangerous feedback loops that can destabilize beliefs and exacerbate mental illness, necessitating coordinated interventions across clinical, technical, and regulatory domains.
This paper introduces the novel concept of Ethically Sourced Code Generation (ES-CodeGen) as a framework for managing the entire lifecycle of code generation models through ethical and sustainable practices, establishing an 11-dimension taxonomy and identifying key consequences through a comprehensive literature review and practitioner survey.