arXiv subjects

Xuefeng Li

Publications and source records attributed to Xuefeng Li.

At least 37 records · Page 2Linked to original sources

arXiv2025

Generative AI Act II: Test Time Scaling Drives Cognition Engineering

The first generation of Large Language Models - what might be called "Act I" of generative AI (2020-2023) - achieved remarkable success through massive parameter and data scaling, yet exhibited fundamental limitations such as knowledge latency, shallow reasoning, and constrained cognitive processes. During this era, prompt engineering emerged as our primary interface with AI, enabling dialogue-level communication through natural language. We now witness the emergence of "Act II" (2024-present), where models are transitioning from knowledge-retrieval systems (in latent space) to thought-construction engines through test-time scaling techniques. This new paradigm establishes a mind-level connection with AI through language-based thoughts. In this paper, we clarify the conceptual foundations of cognition engineering and explain why this moment is critical for its development. We systematically break down these advanced approaches through comprehensive tutorials and optimized implementations, democratizing access to cognition engineering and enabling every practitioner to participate in AI's second act. We provide a regularly updated collection of papers on test-time scaling in the GitHub Repository: https://github.com/GAIR-NLP/cognition-engineering

cs.CL↗

arXiv2025

ToRL: Scaling Tool-Integrated RL

We introduce ToRL (Tool-Integrated Reinforcement Learning), a framework for training large language models (LLMs) to autonomously use computational tools via reinforcement learning. Unlike supervised fine-tuning, ToRL allows models to explore and discover optimal strategies for tool use. Experiments with Qwen2.5-Math models show significant improvements: ToRL-7B reaches 43.3\% accuracy on AIME~24, surpassing reinforcement learning without tool integration by 14\% and the best existing Tool-Integrated Reasoning (TIR) model by 17\%. Further analysis reveals emergent behaviors such as strategic tool invocation, self-regulation of ineffective code, and dynamic adaptation between computational and analytical reasoning, all arising purely through reward-driven learning.

cs.CL↗

arXiv2025

Multi-modal expressive personality recognition in data non-ideal audiovisual based on multi-scale feature enhancement and modal augment

Automatic personality recognition is a research hotspot in the intersection of computer science and psychology, and in human-computer interaction, personalised has a wide range of applications services and other scenarios. In this paper, an end-to-end multimodal performance personality is established for both visual and auditory modal datarecognition network , and the through feature-level fusion , which effectively of the two modalities is carried out the cross-attention mechanismfuses the features of the two modal data; and a is proposed multiscale feature enhancement modalitiesmodule , which enhances for visual and auditory boththe expression of the information of effective the features and suppresses the interference of the redundant information. In addition, during the training process, this paper proposes a modal enhancement training strategy to simulate non-ideal such as modal loss and noise interferencedata situations , which enhances the adaptability ofand the model to non-ideal data scenarios improves the robustness of the model. Experimental results show that the method proposed in this paper is able to achieve an average Big Five personality accuracy of , which outperforms existing 0.916 on the personality analysis dataset ChaLearn First Impressionother methods based on audiovisual and audio-visual both modalities. The ablation experiments also validate our proposed , respectivelythe contribution of module and modality enhancement strategy to the model performance. Finally, we simulate in the inference phase multi-scale feature enhancement six non-ideal data scenarios to verify the modal enhancement strategy's improvement in model robustness.

cs.SD↗

arXiv2025

OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI

The evolution of Artificial Intelligence (AI) has been significantly accelerated by advancements in Large Language Models (LLMs) and Large Multimodal Models (LMMs), gradually showcasing potential cognitive reasoning abilities in problem-solving and scientific discovery (i.e., AI4Science) once exclusive to human intellect. To comprehensively evaluate current models' performance in cognitive reasoning abilities, we introduce OlympicArena, which includes 11,163 bilingual problems across both text-only and interleaved text-image modalities. These challenges encompass a wide range of disciplines spanning seven fields and 62 international Olympic competitions, rigorously examined for data leakage. We argue that the challenges in Olympic competition problems are ideal for evaluating AI's cognitive reasoning due to their complexity and interdisciplinary nature, which are essential for tackling complex scientific challenges and facilitating discoveries. Beyond evaluating performance across various disciplines using answer-only criteria, we conduct detailed experiments and analyses from multiple perspectives. We delve into the models' cognitive reasoning abilities, their performance across different modalities, and their outcomes in process-level evaluations, which are vital for tasks requiring complex reasoning with lengthy solutions. Our extensive evaluations reveal that even advanced models like GPT-4o only achieve a 39.97% overall accuracy, illustrating current AI limitations in complex reasoning and multimodal integration. Through the OlympicArena, we aim to advance AI towards superintelligence, equipping it to address more complex challenges in science and beyond. We also provide a comprehensive set of resources to support AI research, including a benchmark dataset, an open-source annotation platform, a detailed evaluation tool, and a leaderboard with automatic submission features.

cs.CL↗

arXiv2025

Impact of Quantum Well Thickness on Efficiency Loss in InGaN/GaN LEDs: Challenges for Thin-Well Designs

We investigate the impact of quantum well (QW) thickness on efficiency loss in c-plane InGaN/GaN LEDs using a small-signal electroluminescence (SSEL) technique. Multiple mechanisms related to efficiency loss are independently examined, including injection efficiency, carrier density vs. current density relationship, phase space filling (PSF), quantum confined stark effect (QCSE), and Coulomb enhancement. An optimal QW thickness of around 2.7 nm in these InGaN/GaN LEDs was determined for quantum wells having constant In composition. Despite better control of deep-level defects and lower carrier density at a given current density, LEDs with thin QWs still suffer from an imbalance of enhancement effects on the radiative and intrinsic Auger-Meitner recombination coefficients. The imbalance of enhancement effects results in a decline in internal quantum efficiency (IQE) and radiative efficiency with decreasing QW thickness at low current density in LEDs with QW thicknesses below 2.7 nm. We also investigate how LED modulation bandwidth varies with quantum well thickness, identifying the key trends and their implications for device performance.

physics.app-ph↗

arXiv2025

LIMR: Less is More for RL Scaling

In this paper, we ask: what truly determines the effectiveness of RL training data for enhancing language models' reasoning capabilities? While recent advances like o1, Deepseek R1, and Kimi1.5 demonstrate RL's potential, the lack of transparency about training data requirements has hindered systematic progress. Starting directly from base models without distillation, we challenge the assumption that scaling up RL training data inherently improves performance. we demonstrate that a strategically selected subset of just 1,389 samples can outperform the full 8,523-sample dataset. We introduce Learning Impact Measurement (LIM), an automated method to evaluate and prioritize training samples based on their alignment with model learning trajectories, enabling efficient resource utilization and scalable implementation. Our method achieves comparable or even superior performance using only 1,389 samples versus the full 8,523 samples dataset. Notably, while recent data-efficient approaches (e.g., LIMO and s1) show promise with 32B-scale models, we find it significantly underperforms at 7B-scale through supervised fine-tuning (SFT). In contrast, our RL-based LIMR achieves 16.7% higher accuracy on AIME24 and outperforms LIMO and s1 by 13.0% and 22.2% on MATH500. These results fundamentally reshape our understanding of RL scaling in LLMs, demonstrating that precise sample selection, rather than data scale, may be the key to unlocking enhanced reasoning capabilities. For reproducible research and future innovation, we are open-sourcing LIMR, including implementation of LIM, training and evaluation code, curated datasets, and trained models at https://github.com/GAIR-NLP/LIMR.

cs.LG↗

arXiv2025

Evaluating Mathematical Reasoning Beyond Accuracy

The leaderboard of Large Language Models (LLMs) in mathematical tasks has been continuously updated. However, the majority of evaluations focus solely on the final results, neglecting the quality of the intermediate steps. This oversight can mask underlying problems, such as logical errors or unnecessary steps in the reasoning process. To measure reasoning beyond final-answer accuracy, we introduce ReasonEval, a new methodology for evaluating the quality of reasoning steps. ReasonEval employs validity and redundancy to characterize the reasoning quality, as well as accompanying LLMs to assess them automatically. We explore different design options for the LLM-based evaluators and empirically demonstrate that ReasonEval, when instantiated with base models possessing strong mathematical knowledge and trained with high-quality labeled data, consistently outperforms baseline methods in the meta-evaluation datasets. We also highlight the strong generalization capabilities of ReasonEval. By utilizing ReasonEval to evaluate LLMs specialized in math, we find that an increase in final-answer accuracy does not necessarily guarantee an improvement in the overall quality of the reasoning steps for challenging mathematical problems. Additionally, we observe that ReasonEval can play a significant role in data selection. We open-source the best-performing model, meta-evaluation script, and all evaluation results to facilitate future research.

cs.CL↗

arXiv2024

O1 Replication Journey -- Part 2: Surpassing O1-preview through Simple Distillation, Big Progress or Bitter Lesson?

This paper presents a critical examination of current approaches to replicating OpenAI's O1 model capabilities, with particular focus on the widespread but often undisclosed use of knowledge distillation techniques. While our previous work explored the fundamental technical path to O1 replication, this study reveals how simple distillation from O1's API, combined with supervised fine-tuning, can achieve superior performance on complex mathematical reasoning tasks. Through extensive experiments, we show that a base model fine-tuned on simply tens of thousands of samples O1-distilled long-thought chains outperforms O1-preview on the American Invitational Mathematics Examination (AIME) with minimal technical complexity. Moreover, our investigation extends beyond mathematical reasoning to explore the generalization capabilities of O1-distilled models across diverse tasks: hallucination, safety and open-domain QA. Notably, despite training only on mathematical problem-solving data, our models demonstrated strong generalization to open-ended QA tasks and became significantly less susceptible to sycophancy after fine-tuning. We deliberately make this finding public to promote transparency in AI research and to challenge the current trend of obscured technical claims in the field. Our work includes: (1) A detailed technical exposition of the distillation process and its effectiveness, (2) A comprehensive benchmark framework for evaluating and categorizing O1 replication attempts based on their technical transparency and reproducibility, (3) A critical discussion of the limitations and potential risks of over-relying on distillation approaches, our analysis culminates in a crucial bitter lesson: while the pursuit of more capable AI systems is important, the development of researchers grounded in first-principles thinking is paramount.

cs.CL↗

arXiv2024

Prior-based Objective Inference Mining Potential Uncertainty for Facial Expression Recognition

Annotation ambiguity caused by the inherent subjectivity of visual judgment has always been a major challenge for Facial Expression Recognition (FER) tasks, particularly for largescale datasets from in-the-wild scenarios. A potential solution is the evaluation of relatively objective emotional distributions to help mitigate the ambiguity of subjective annotations. To this end, this paper proposes a novel Prior-based Objective Inference (POI) network. This network employs prior knowledge to derive a more objective and varied emotional distribution and tackles the issue of subjective annotation ambiguity through dynamic knowledge transfer. POI comprises two key networks: Firstly, the Prior Inference Network (PIN) utilizes the prior knowledge of AUs and emotions to capture intricate motion details. To reduce over-reliance on priors and facilitate objective emotional inference, PIN aggregates inferential knowledge from various key facial subregions, encouraging mutual learning. Secondly, the Target Recognition Network (TRN) integrates subjective emotion annotations and objective inference soft labels provided by the PIN, fostering an understanding of inherent facial expression diversity, thus resolving annotation ambiguity. Moreover, we introduce an uncertainty estimation module to quantify and balance facial expression confidence. This module enables a flexible approach to dealing with the uncertainties of subjective annotations. Extensive experiments show that POI exhibits competitive performance on both synthetic noisy datasets and multiple real-world datasets. All codes and training logs will be publicly available at https://github.com/liuhw01/POI.

cs.CV↗

arXiv2024

MathPile: A Billion-Token-Scale Pretraining Corpus for Math

High-quality, large-scale corpora are the cornerstone of building foundation models. In this work, we introduce MathPile, a diverse and high-quality math-centric corpus comprising about 9.5 billion tokens. Throughout its creation, we adhered to the principle of "less is more", firmly believing in the supremacy of data quality over quantity, even in the pre-training phase. Our meticulous data collection and processing efforts included a complex suite of preprocessing, prefiltering, language identification, cleaning, filtering, and deduplication, ensuring the high quality of our corpus. Furthermore, we performed data contamination detection on downstream benchmark test sets to eliminate duplicates and conducted continual pre-training experiments, booting the performance on common mathematical reasoning benchmarks. We aim for our MathPile to boost language models' mathematical reasoning abilities and open-source its different versions and processing scripts to advance the field.

cs.CL↗

arXiv2024

OpenResearcher: Unleashing AI for Accelerated Scientific Research

The rapid growth of scientific literature imposes significant challenges for researchers endeavoring to stay updated with the latest advancements in their fields and delve into new areas. We introduce OpenResearcher, an innovative platform that leverages Artificial Intelligence (AI) techniques to accelerate the research process by answering diverse questions from researchers. OpenResearcher is built based on Retrieval-Augmented Generation (RAG) to integrate Large Language Models (LLMs) with up-to-date, domain-specific knowledge. Moreover, we develop various tools for OpenResearcher to understand researchers' queries, search from the scientific literature, filter retrieved information, provide accurate and comprehensive answers, and self-refine these answers. OpenResearcher can flexibly use these tools to balance efficiency and effectiveness. As a result, OpenResearcher enables researchers to save time and increase their potential to discover new insights and drive scientific breakthroughs. Demo, video, and code are available at: https://github.com/GAIR-NLP/OpenResearcher.

cs.IR↗

arXiv2024

Prediction of Large Solar Flares Based on SHARP and HED Magnetic Field Parameters

The existing flare prediction primarily relies on photospheric magnetic field parameters from the entire active region (AR), such as Space-Weather HMI Activity Region Patches (SHARP) parameters. However, these parameters may not capture the details the AR evolution preceding flares. The magnetic structure within the core area of an AR is essential for predicting large solar flares. This paper utilizes the area of high photospheric free energy density (HED region) as a proxy for the AR core region. We construct two datasets: SHARP and HED datasets. The ARs contained in both datasets are identical. Furthermore, the start and end times for the same AR in both datasets are identical. We develop six models for 24-hour solar flare forecasting, utilizing SHARP and HED datasets. We then compare their categorical and probabilistic forecasting performance. Additionally, we conduct an analysis of parameter importance. The main results are as follows: (1) Among the six solar flare prediction models, the models using HED parameters outperform those using SHARP parameters in both categorical and probabilistic prediction, indicating the important role of the HED region in the flare initiation process. (2) The Transformer flare prediction model stands out significantly in True Skill Statistic (TSS) and Brier Skill Score (BSS), surpassing the other models. (3) In parameter importance analysis, the total photospheric free magnetic energy density ($\mathrm {E_{free}}$) within the HED parameters excels in both categorical and probabilistic forecasting. Similarly, among the SHARP parameters, the R_VALUE stands out as the most effective parameter for both categorical and probabilistic forecasting.

astro-ph.SR↗

arXiv2024

O1 Replication Journey: A Strategic Progress Report -- Part 1

This paper introduces a pioneering approach to artificial intelligence research, embodied in our O1 Replication Journey. In response to the announcement of OpenAI's groundbreaking O1 model, we embark on a transparent, real-time exploration to replicate its capabilities while reimagining the process of conducting and communicating AI research. Our methodology addresses critical challenges in modern AI research, including the insularity of prolonged team-based projects, delayed information sharing, and the lack of recognition for diverse contributions. By providing comprehensive, real-time documentation of our replication efforts, including both successes and failures, we aim to foster open science, accelerate collective advancement, and lay the groundwork for AI-driven scientific discovery. Our research progress report diverges significantly from traditional research papers, offering continuous updates, full process transparency, and active community engagement throughout the research journey. Technologically, we proposed the journey learning paradigm, which encourages models to learn not just shortcuts, but the complete exploration process, including trial and error, reflection, and backtracking. With only 327 training samples and without any additional tricks, journey learning outperformed conventional supervised learning by over 8\% on the MATH dataset, demonstrating its extremely powerful potential. We believe this to be the most crucial component of O1 technology that we have successfully decoded. We share valuable resources including technical hypotheses and insights, cognitive exploration maps, custom-developed tools, etc at https://github.com/GAIR-NLP/O1-Journey.

cs.AI↗

arXiv2024

Multi-Programming Language Ensemble for Code Generation in Large Language Model

Large language models (LLMs) have significantly improved code generation, particularly in one-pass code generation. However, most existing approaches focus solely on generating code in a single programming language, overlooking the potential of leveraging the multi-language capabilities of LLMs. LLMs have varying patterns of errors across different languages, suggesting that a more robust approach could be developed by leveraging these multi-language outputs. In this study, we propose Multi-Programming Language Ensemble (MPLE), a novel ensemble-based method that utilizes code generation across multiple programming languages to enhance overall performance. By treating each language-specific code generation process as an individual "weak expert" and effectively integrating their outputs, our method mitigates language-specific errors and biases. This multi-language ensemble strategy leverages the complementary strengths of different programming languages, enabling the model to produce more accurate and robust code. Our approach can be seamlessly integrated with commonly used techniques such as the reflection algorithm and Monte Carlo tree search to improve code generation quality further. Experimental results show that our framework consistently enhances baseline performance by up to 17.92% on existing benchmarks (HumanEval and HumanEval-plus), with a standout result of 96.25% accuracy on the HumanEval benchmark, achieving new state-of-the-art results across various LLM models. The code will be released at https://github.com/NinjaTech-AI/MPLE

cs.CL↗

arXiv2024

NinjaLLM: Fast, Scalable and Cost-effective RAG using Amazon SageMaker and AWS Trainium and Inferentia2

Retrieval-augmented generation (RAG) techniques are widely used today to retrieve and present information in a conversational format. This paper presents a set of enhancements to traditional RAG techniques, focusing on large language models (LLMs) fine-tuned and hosted on AWS Trainium and Inferentia2 AI chips via SageMaker. These chips are characterized by their elasticity, affordability, and efficient performance for AI compute tasks. Besides enabling deployment on these chips, this work aims to improve tool usage, add citation capabilities, and mitigate the risks of hallucinations and unsafe responses due to context bias. We benchmark our RAG system's performance on the Natural Questions and HotPotQA datasets, achieving an accuracy of 62% and 59% respectively, exceeding other models such as DBRX and Mixtral Instruct.

cs.CL↗

arXiv2024

Progress or Regress? Self-Improvement Reversal in Post-training

Self-improvement through post-training methods such as iterative preference learning has been acclaimed for enhancing the problem-solving capabilities (e.g., mathematical reasoning) of Large Language Models (LLMs) without human intervention. However, as exploration deepens, it becomes crucial to assess whether these improvements genuinely signify progress in solving more challenging problems or if they could lead to unintended regressions. To address this, we propose a comprehensive evaluative framework that goes beyond the superficial pass@1 metric to scrutinize the underlying enhancements of post-training paradigms for self-improvement. Through rigorous experimentation and analysis across diverse problem-solving tasks, the empirical results point out the phenomenon of \emph{self-improvement reversal}, where models showing improved performance across benchmarks will paradoxically exhibit declines in broader, essential capabilities, like output diversity and out-of-distribution (OOD) generalization. These findings indicate that current self-improvement practices through post-training are inadequate for equipping models to tackle more complex problems. Furthermore, they underscore the necessity of our critical evaluation metrics in discerning the \emph{progress or regress} dichotomy for self-improving LLMs.

cs.CL↗

arXiv2024

Reformatted Alignment

The quality of finetuning data is crucial for aligning large language models (LLMs) with human values. Current methods to improve data quality are either labor-intensive or prone to factual errors caused by LLM hallucinations. This paper explores elevating the quality of existing instruction data to better align with human values, introducing a simple and effective approach named ReAlign, which reformats the responses of instruction data into a format that better aligns with pre-established criteria and the collated evidence. This approach minimizes human annotation, hallucination, and the difficulty in scaling, remaining orthogonal to existing alignment techniques. Experimentally, ReAlign significantly boosts the general alignment ability, math reasoning, factuality, and readability of the LLMs. Encouragingly, without introducing any additional data or advanced training techniques, and merely by reformatting the response, LLaMA-2-13B's mathematical reasoning ability on GSM8K can be improved from 46.77% to 56.63% in accuracy. Additionally, a mere 5% of ReAlign data yields a 67% boost in general alignment ability measured by the Alpaca dataset. This work highlights the need for further research into the science and mechanistic interpretability of LLMs. We have made the associated code and data publicly accessible to support future studies at https://github.com/GAIR-NLP/ReAlign.

cs.CL↗

arXiv2024

Pipelined Biomedical Event Extraction Rivaling Joint Learning

Biomedical event extraction is an information extraction task to obtain events from biomedical text, whose targets include the type, the trigger, and the respective arguments involved in an event. Traditional biomedical event extraction usually adopts a pipelined approach, which contains trigger identification, argument role recognition, and finally event construction either using specific rules or by machine learning. In this paper, we propose an n-ary relation extraction method based on the BERT pre-training model to construct Binding events, in order to capture the semantic information about an event's context and its participants. The experimental results show that our method achieves promising results on the GE11 and GE13 corpora of the BioNLP shared task with F1 scores of 63.14% and 59.40%, respectively. It demonstrates that by significantly improving theperformance of Binding events, the overall performance of the pipelined event extraction approach or even exceeds those of current joint learning methods.

cs.CL↗