arXiv subjects

Yanjun Chen

Publications and source records attributed to Yanjun Chen.

At least 37 records · Page 2Linked to original sources

arXiv2025

Response time of electrons to light in strong-field ionization of polar molecules

We study tunneling ionization of HeH+ in strong elliptical laser fields numerically and analytically. The calculated photoelectron momentum distribution (PMD) show two different offset angles corresponding to ionization events occurring in the first and the second half cycles of one laser cycle. When the larger angle is greater than the angle of a model symmetric molecule with a similar ionization potential to the polar molecule, the smaller angle is smaller than the symmetric molecule. Using a developed strong-field model that consider effects of both the permanent dipole (PD) and the asymmetric Coulomb potential, we are able to quantitatively reproduce these phenomena. We show that the PD effect can increase (decrease) the response time of electrons within polar molecules to light in photoemission, thereby increasing (decreasing) the offset angle related to the first (second) half cycle of a laser cycle. The laser-dressed asymmetric Coulomb potential near the atomic nuclei also plays an important role in the sub-cycle-related response time and offset angle. This model may be useful for quantitatively studying attosecond ionization dynamics of polar molecules in strong laser fields.

physics.atom-ph↗

arXiv2025

PricingLogic: Evaluating LLMs Reasoning on Complex Tourism Pricing Tasks

We present PricingLogic, the first benchmark that probes whether Large Language Models(LLMs) can reliably automate tourism-related prices when multiple, overlapping fare rules apply. Travel agencies are eager to offload this error-prone task onto AI systems; however, deploying LLMs without verified reliability could result in significant financial losses and erode customer trust. PricingLogic comprises 300 natural-language questions based on booking requests derived from 42 real-world pricing policies, spanning two levels of difficulty: (i) basic customer-type pricing and (ii)bundled-tour calculations involving interacting discounts. Evaluations of a line of LLMs reveal a steep performance drop on the harder tier,exposing systematic failures in rule interpretation and arithmetic reasoning.These results highlight that, despite their general capabilities, today's LLMs remain unreliable in revenue-critical applications without further safeguards or domain adaptation. Our code and dataset are available at https://github.com/EIT-NLP/PricingLogic.

cs.AI↗

arXiv2025

LLaSO: A Foundational Framework for Reproducible Research in Large Language and Speech Model

The development of Large Speech-Language Models (LSLMs) has been slowed by fragmented architectures and a lack of transparency, hindering the systematic comparison and reproducibility of research. Unlike in the vision-language domain, the LSLM field suffers from the common practice of releasing model weights without their corresponding training data and configurations. To address these critical gaps, we introduce LLaSO, the first fully open, end-to-end framework for large-scale speech-language modeling. LLaSO provides the community with three essential resources: (1) LLaSO-Align, a 12M-instance speech-text alignment corpus; (2) LLaSO-Instruct, a 13.5M-instance multi-task instruction-tuning dataset; and (3) LLaSO-Eval, a reproducible benchmark for standardized evaluation. To validate our framework, we build and release LLaSO-Base, a 3.8B-parameter reference model trained exclusively on our public data. It achieves a normalized score of 0.72, establishing a strong, reproducible baseline that surpasses comparable models. Our analysis reveals that while broader training coverage enhances performance, significant generalization gaps persist on unseen tasks, particularly in pure audio scenarios. By releasing the complete stack of data, benchmarks, and models, LLaSO establishes a foundational open standard to unify research efforts and accelerate community-driven progress in LSLMs. We release the code, dataset, pretrained models, and results in https://github.com/EIT-NLP/LLaSO.

cs.CL↗

arXiv2025

CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents

The development of autonomous agents increasingly relies on Multimodal Language Models (MLMs) to perform tasks described in natural language with GUI environments, such as websites, desktop computers, or mobile phones. Existing benchmarks for MLM agents in interactive environments are limited by their focus on a single environment, lack of detailed and generalized evaluation methods, and the complexities of constructing tasks and evaluators. To overcome these limitations, we introduce Crab, the first agent benchmark framework designed to support cross-environment tasks, incorporating a graph-based fine-grained evaluation method and an efficient mechanism for task and evaluator construction. Our framework supports multiple devices and can be easily extended to any environment with a Python interface. Leveraging Crab, we developed a cross-platform Crab Benchmark-v0 comprising 120 tasks in computer desktop and mobile phone environments. We evaluated four advanced MLMs using different single and multi-agent system configurations on this benchmark. The experimental results demonstrate that the single agent with GPT-4o achieves the best completion ratio of 38.01%. All framework code, agent code, and task datasets are publicly available at https://github.com/camel-ai/crab.

cs.AI↗

arXiv2025

Unveiling the Key Factors for Distilling Chain-of-Thought Reasoning

Large Language Models (LLMs) excel in reasoning tasks through Chain-of-Thought (CoT) prompting. However, CoT prompting greatly increases computational demands, which has prompted growing interest in distilling CoT capabilities into Small Language Models (SLMs). This study systematically examines the factors influencing CoT distillation, including the choice of granularity, format and teacher model. Through experiments involving four teacher models and seven student models across seven mathematical and commonsense reasoning datasets, we uncover three key findings: (1) Unlike LLMs, SLMs exhibit a non-monotonic relationship with granularity, with stronger models benefiting from finer-grained reasoning and weaker models performing better with simpler CoT supervision; (2) CoT format significantly impacts LLMs but has minimal effect on SLMs, likely due to their reliance on supervised fine-tuning rather than pretraining preferences; (3) Stronger teacher models do NOT always produce better student models, as diversity and complexity in CoT supervision can outweigh accuracy alone. These findings emphasize the need to tailor CoT strategies to specific student model, offering actionable insights for optimizing CoT distillation in SLMs. The code and datasets are available at https://github.com/EIT-NLP/Distilling-CoT-Reasoning.

cs.CL↗

arXiv2025

MA-ROESL: Motion-aware Rapid Reward Optimization for Efficient Robot Skill Learning from Single Videos

Vision-language models (VLMs) have demonstrated excellent high-level planning capabilities, enabling locomotion skill learning from video demonstrations without the need for meticulous human-level reward design. However, the improper frame sampling method and low training efficiency of current methods remain a critical bottleneck, resulting in substantial computational overhead and time costs. To address this limitation, we propose Motion-aware Rapid Reward Optimization for Efficient Robot Skill Learning from Single Videos (MA-ROESL). MA-ROESL integrates a motion-aware frame selection method to implicitly enhance the quality of VLM-generated reward functions. It further employs a hybrid three-phase training pipeline that improves training efficiency via rapid reward optimization and derives the final policy through online fine-tuning. Experimental results demonstrate that MA-ROESL significantly enhances training efficiency while faithfully reproducing locomotion skills in both simulated and real-world settings, thereby underscoring its potential as a robust and scalable framework for efficient robot locomotion skill learning from video demonstrations.

cs.RO↗

arXiv2025

Rethinking Soft Actor-Critic in High-Dimensional Action Spaces: The Cost of Ignoring Distribution Shift

Soft Actor-Critic algorithm is widely recognized for its robust performance across a range of deep reinforcement learning tasks, where it leverages the tanh transformation to constrain actions within bounded limits. However, this transformation induces a distribution shift, distorting the original Gaussian action distribution and potentially leading the policy to select suboptimal actions, particularly in high-dimensional action spaces. In this paper, we conduct a comprehensive theoretical and empirical analysis of this distribution shift, deriving the precise probability density function (PDF) for actions following the tanh transformation to clarify the misalignment introduced between the transformed distribution's mode and the intended action output. We substantiate these theoretical insights through extensive experiments on high-dimensional tasks within the HumanoidBench benchmark. Our findings indicate that accounting for this distribution shift substantially enhances SAC's performance, resulting in notable improvements in cumulative rewards, sample efficiency, and reliability across tasks. These results underscore a critical consideration for SAC and similar algorithms: addressing transformation-induced distribution shifts is essential to optimizing policy effectiveness in high-dimensional deep reinforcement learning environments, thereby expanding the robustness and applicability of SAC in complex control tasks.

cs.LG↗

arXiv2025

Fine-Grained and Multi-Dimensional Metrics for Document-Level Machine Translation

Large language models (LLMs) have excelled in various NLP tasks, including machine translation (MT), yet most studies focus on sentence-level translation. This work investigates the inherent capability of instruction-tuned LLMs for document-level translation (docMT). Unlike prior approaches that require specialized techniques, we evaluate LLMs by directly prompting them to translate entire documents in a single pass. Our results show that this method improves translation quality compared to translating sentences separately, even without document-level fine-tuning. However, this advantage is not reflected in BLEU scores, which often favor sentence-based translations. We propose using the LLM-as-a-judge paradigm for evaluation, where GPT-4 is used to assess document coherence, accuracy, and fluency in a more nuanced way than n-gram-based metrics. Overall, our work demonstrates that instruction-tuned LLMs can effectively leverage document context for translation. However, we caution against using BLEU scores for evaluating docMT, as they often provide misleading outcomes, failing to capture the quality of document-level translation. Code and the outputs from GPT4-as-a-judge are available at https://github.com/EIT-NLP/BLEUless_DocMT

cs.CL↗

arXiv2025

Breaking the Pre-Planning Barrier: Adaptive Real-Time Coordination of Heterogeneous UAVs

Unmanned Aerial Vehicles (UAVs) offer significant potential in dynamic, perception-intensive tasks such as search and rescue and environmental monitoring; however, their effectiveness is severely restricted by conventional pre-planned routing methods, which lack the flexibility to respond in real-time to evolving task demands, unexpected disturbances, and localized view limitations in real-world scenarios. To address this fundamental limitation, we introduce a novel multi-agent reinforcement learning framework named \textbf{H}eterogeneous \textbf{G}raph \textbf{A}ttention \textbf{M}ulti-agent Deep Deterministic Policy Gradient (HGAM), uniquely designed to enable adaptive real-time coordination between mission UAVs (MUAVs) and charging UAVs (CUAVs). HGAM specifically addresses the previously unsolved challenge of enabling precise, decentralized continuous-action coordination solely based on local, heterogeneous graph-based observations. Extensive simulations demonstrate that HGAM substantially surpasses existing methods, achieving, for example, a 30\% improvement in data collection coverage and a 20\% increase in charging efficiency, providing crucial insights and foundations for the future deployment of intelligent, flexible UAV networks in complex, dynamic environments.

cs.MA↗

arXiv2025

PRISM: Preference Refinement via Implicit Scene Modeling for 3D Vision-Language Preference-Based Reinforcement Learning

We propose PRISM, a novel framework designed to overcome the limitations of 2D-based Preference-Based Reinforcement Learning (PBRL) by unifying 3D point cloud modeling and future-aware preference refinement. At its core, PRISM adopts a 3D Point Cloud-Language Model (3D-PC-LLM) to mitigate occlusion and viewpoint biases, ensuring more stable and spatially consistent preference signals. Additionally, PRISM leverages Chain-of-Thought (CoT) reasoning to incorporate long-horizon considerations, thereby preventing the short-sighted feedback often seen in static preference comparisons. In contrast to conventional PBRL techniques, this integration of 3D perception and future-oriented reasoning leads to significant gains in preference agreement rates, faster policy convergence, and robust generalization across unseen robotic environments. Our empirical results, spanning tasks such as robotic manipulation and autonomous navigation, highlight PRISM's potential for real-world applications where precise spatial understanding and reliable long-term decision-making are critical. By bridging 3D geometric awareness with CoT-driven preference modeling, PRISM establishes a comprehensive foundation for scalable, human-aligned reinforcement learning.

cs.CL↗

arXiv2025

Integrating Chain-of-Thought for Multimodal Alignment: A Study on 3D Vision-Language Learning

Chain-of-Thought (CoT) reasoning has proven effective in natural language tasks but remains underexplored in multimodal alignment. This study investigates its integration into 3D vision-language learning by embedding structured reasoning into alignment training. We introduce the 3D-CoT Benchmark, a dataset with hierarchical CoT annotations covering shape recognition, functional inference, and causal reasoning. Through controlled experiments, we compare CoT-structured and standard textual annotations across large reasoning models (LRMs) and large language models (LLMs). Our evaluation employs a dual-layer framework assessing both intermediate reasoning and final inference quality. Extensive experiments demonstrate that CoT significantly improves 3D semantic grounding, with LRMs leveraging CoT more effectively than LLMs. Furthermore, we highlight that annotation structure influences performance-explicit reasoning markers aid LLMs, while unmarked CoT better aligns with LRM inference patterns. Our analyses suggest that CoT is crucial for enhancing multimodal reasoning, with implications beyond 3D tasks. The dataset will be publicly available at https://huggingface.co/datasets/Battam/3D-CoT

cs.CL↗

arXiv2024

ArchiTone: A LEGO-Inspired Gamified System for Visualized Music Education

Participation in music activities has many benefits, but often requires music theory knowledge and aural skills, which can be challenging for beginners. To help them engage more easily, it's crucial to adopt teaching strategies that lower these barriers. Informed by formative investigation and inspired by LEGO, we introduce ArchiTone, a gamified system that employs constructivism by visualizing music theory concepts as musical blocks and buildings for music education. This system includes two modes: Learning Mode, which involves recognizing and learning common musical blocks through familiar musical works; Creation Mode, which allows learners to freely create and combine musical blocks to produce new musical works. User studies demonstrate that our gamified system is not only more engaging than traditional music education methods but also more effective in helping learners understand abstract music theory and apply it to music praxis. Additionally, learners demonstrate superior performance on music theory tasks after using ArchiTone.

cs.HC↗

arXiv2024

The Accuracy Paradox in RLHF: When Better Reward Models Don't Yield Better Language Models

Reinforcement Learning from Human Feedback significantly enhances Natural Language Processing by aligning language models with human expectations. A critical factor in this alignment is the strength of reward models used during training. This study explores whether stronger reward models invariably lead to better language models. In this paper, through experiments on relevance, factuality, and completeness tasks using the QA-FEEDBACK dataset and reward models based on Longformer, we uncover a surprising paradox: language models trained with moderately accurate reward models outperform those guided by highly accurate ones. This challenges the widely held belief that stronger reward models always lead to better language models, and opens up new avenues for future research into the key factors driving model performance and how to choose the most suitable reward models. Code and additional details are available at https://github.com/EIT-NLP/AccuracyParadox-RLHF.

cs.CL↗

arXiv2023

VIMA: General Robot Manipulation with Multimodal Prompts

Prompt-based learning has emerged as a successful paradigm in natural language processing, where a single general-purpose language model can be instructed to perform any task specified by input prompts. Yet task specification in robotics comes in various forms, such as imitating one-shot demonstrations, following language instructions, and reaching visual goals. They are often considered different tasks and tackled by specialized models. We show that a wide spectrum of robot manipulation tasks can be expressed with multimodal prompts, interleaving textual and visual tokens. Accordingly, we develop a new simulation benchmark that consists of thousands of procedurally-generated tabletop tasks with multimodal prompts, 600K+ expert trajectories for imitation learning, and a four-level evaluation protocol for systematic generalization. We design a transformer-based robot agent, VIMA, that processes these prompts and outputs motor actions autoregressively. VIMA features a recipe that achieves strong model scalability and data efficiency. It outperforms alternative designs in the hardest zero-shot generalization setting by up to $2.9\times$ task success rate given the same training data. With $10\times$ less training data, VIMA still performs $2.7\times$ better than the best competing variant. Code and video demos are available at https://vimalabs.github.io/

cs.RO↗

arXiv2023

Towards Diverse Temporal Grounding under Single Positive Labels

Temporal grounding aims to retrieve moments of the described event within an untrimmed video by a language query. Typically, existing methods assume annotations are precise and unique, yet one query may describe multiple moments in many cases. Hence, simply taking it as a one-vs-one mapping task and striving to match single-label annotations will inevitably introduce false negatives during optimization. In this study, we reformulate this task as a one-vs-many optimization problem under the condition of single positive labels. The unlabeled moments are considered unobserved rather than negative, and we explore mining potential positive moments to assist in multiple moment retrieval. In this setting, we propose a novel Diverse Temporal Grounding framework, termed DTG-SPL, which mainly consists of a positive moment estimation (PME) module and a diverse moment regression (DMR) module. PME leverages semantic reconstruction information and an expected positive regularization to uncover potential positive moments in an online fashion. Under the supervision of these pseudo positives, DMR is able to localize diverse moments in parallel that meet different users. The entire framework allows for end-to-end optimization as well as fast inference. Extensive experiments on Charades-STA and ActivityNet Captions show that our method achieves superior performance in terms of both single-label and multi-label metrics.

cs.CV↗

arXiv2021

Embracing Uncertainty: Decoupling and De-bias for Robust Temporal Grounding

Temporal grounding aims to localize temporal boundaries within untrimmed videos by language queries, but it faces the challenge of two types of inevitable human uncertainties: query uncertainty and label uncertainty. The two uncertainties stem from human subjectivity, leading to limited generalization ability of temporal grounding. In this work, we propose a novel DeNet (Decoupling and De-bias) to embrace human uncertainty: Decoupling - We explicitly disentangle each query into a relation feature and a modified feature. The relation feature, which is mainly based on skeleton-like words (including nouns and verbs), aims to extract basic and consistent information in the presence of query uncertainty. Meanwhile, modified feature assigned with style-like words (including adjectives, adverbs, etc) represents the subjective information, and thus brings personalized predictions; De-bias - We propose a de-bias mechanism to generate diverse predictions, aim to alleviate the bias caused by single-style annotations in the presence of label uncertainty. Moreover, we put forward new multi-label metrics to diversify the performance evaluation. Extensive experiments show that our approach is more effective and robust than state-of-the-arts on Charades-STA and ActivityNet Captions datasets.

cs.CV↗

arXiv2021

Alignment dependence of photoelectron momentum distributions for diatomic molecules N$_2$ in strong elliptical laser fields

We study ionization dynamics of aligned diatomic molecules N$_2$ in strong elliptical laser fields experimentally and theoretically. The alignment dependence of photoelectron momentum distributions (PMDs) of N$_2$ measured in experiments is highlighted with comparing to Ar measured synchronously. Our results show that the PMDs of N$_2$ depend strongly on the alignment of the molecule, relative to the main axis of the laser ellipse. In particular, the most-probable electron-emission angle which is often used in attosecond measurement, differs remarkably when changing the molecular alignment. We show that the interplay of two-center interference and tunneling when the electron goes through the laser-Coulomb-formed barrier, plays an important role in these phenomena. Our work gives suggestions on studying ultrafast electron motion inside aligned molecules.

physics.atom-ph↗

arXiv2021

Strong-field response time and its implications on attosecond measurement

To measure and control the electron motion in atoms and molecules by the strong laser field on the attosecond time scale is one of the research frontiers of atomic and molecular photophysics. It involves many new phenomena and processes and raises a series of questions of concepts, theories and methods. Recent studies show that the Coulomb potential can cause the ionization time lag (about 100 attoseconds) between instants of the field maximum and the ionization-rate maximum. This lag can be understood as the response time of the electronic wave function to the strong-field-induced ionization event. It has a profound influence on the subsequent ultrafast dynamics of the ionized electron and can significantly change the time-frequency properties of electron trajectory (an important theoretical tool for attosecond measurement). Here, the research progress of response time and its implications on attosecond measurement are briefly introduced.

physics.atom-ph↗