DataSciBench: An LLM Agent Benchmark for Data Science

This paper presents DataSciBench, a comprehensive benchmark for evaluating Large Language Model (LLM) capabilities in data science. Recent related benchmarks have primarily focused on single tasks, easily obtainable ground truth, and straightforward evaluation metrics, which limits the scope of tasks that can be evaluated. In contrast, DataSciBench is constructed based on a more comprehensive and curated collection of natural and challenging prompts for uncertain ground truth and evaluation metrics. We develop a semi-automated pipeline for generating ground truth (GT) and validating evaluation metrics. This pipeline utilizes and implements an LLM-based self-consistency and human verification strategy to produce accurate GT by leveraging collected prompts, predefined task types, and aggregate functions (metrics). Furthermore, we propose an innovative Task - Function - Code (TFC) framework to assess each code execution outcome based on precisely defined metrics and programmatic rules. Our experimental framework involves testing 6 API-based models, 8 open-source general models, and 9 open-source code generation models using the diverse set of prompts we have gathered. This approach aims to provide a more comprehensive and rigorous evaluation of LLMs in data science, revealing their strengths and weaknesses. Experimental results demonstrate that API-based models outperform open-sourced models on all metrics and Deepseek-Coder-33B-Instruct achieves the highest score among open-sourced models. We release all code and data at https://github.com/THUDM/DataSciBench.

CoSER: Coordinating LLM-Based Persona Simulation of Established Roles

Role-playing language agents (RPLAs) have emerged as promising applications of large language models (LLMs). However, simulating established characters presents a challenging task for RPLAs, due to the lack of authentic character datasets and nuanced evaluation methods using such data. In this paper, we present CoSER, a collection of a high-quality dataset, open models, and an evaluation protocol towards effective RPLAs of established characters. The CoSER dataset covers 17,966 characters from 771 renowned books. It provides authentic dialogues with real-world intricacies, as well as diverse data types such as conversation setups, character experiences and internal thoughts. Drawing from acting methodology, we introduce given-circumstance acting for training and evaluating role-playing LLMs, where LLMs sequentially portray multiple characters in book scenes. Using our dataset, we develop CoSER 8B and CoSER 70B, i.e., advanced open role-playing LLMs built on LLaMA-3.1 models. Extensive experiments demonstrate the value of the CoSER dataset for RPLA training, evaluation and retrieval. Moreover, CoSER 70B exhibits state-of-the-art performance surpassing or matching GPT-4o on our evaluation and three existing benchmarks, i.e., achieving 75.80% and 93.47% accuracy on the InCharacter and LifeChoice benchmarks respectively.

HDCompression: Hybrid-Diffusion Image Compression for Ultra-Low Bitrates

Image compression under ultra-low bitrates remains challenging for both conventional learned image compression (LIC) and generative vector-quantized (VQ) modeling. Conventional LIC suffers from severe artifacts due to heavy quantization, while generative VQ modeling gives poor fidelity due to the mismatch between learned generative priors and specific inputs. In this work, we propose Hybrid-Diffusion Image Compression (HDCompression), a dual-stream framework that utilizes both generative VQ-modeling and diffusion models, as well as conventional LIC, to achieve both high fidelity and high perceptual quality. Different from previous hybrid methods that directly use pre-trained LIC models to generate low-quality fidelity-preserving information from heavily quantized latent, we use diffusion models to extract high-quality complimentary fidelity information from the ground-truth input, which can enhance the system performance in several aspects: improving indices map prediction, enhancing the fidelity-preserving output of the LIC stream, and refining conditioned image reconstruction with VQ-latent correction. In addition, our diffusion model is based on a dense representative vector (DRV), which is lightweight with very simple sampling schedulers. Extensive experiments demonstrate that our HDCompression outperforms the previous conventional LIC, generative VQ-modeling, and hybrid frameworks in both quantitative metrics and qualitative visualization, providing balanced robust compression performance at ultra-low bitrates.

CSR-Bench: Benchmarking LLM Agents in Deployment of Computer Science Research Repositories

The increasing complexity of computer science research projects demands more effective tools for deploying code repositories. Large Language Models (LLMs), such as Anthropic Claude and Meta Llama, have demonstrated significant advancements across various fields of computer science research, including the automation of diverse software engineering tasks. To evaluate the effectiveness of LLMs in handling complex code development tasks of research projects, particularly for NLP/CV/AI/ML/DM topics, we introduce CSR-Bench, a benchmark for Computer Science Research projects. This benchmark assesses LLMs from various aspects including accuracy, efficiency, and deployment script quality, aiming to explore their potential in conducting computer science research autonomously. We also introduce a novel framework, CSR-Agents, that utilizes multiple LLM agents to automate the deployment of GitHub code repositories of computer science research projects. Specifically, by checking instructions from markdown files and interpreting repository structures, the model generates and iteratively improves bash commands that set up the experimental environments and deploy the code to conduct research tasks. Preliminary results from CSR-Bench indicate that LLM agents can significantly enhance the workflow of repository deployment, thereby boosting developer productivity and improving the management of developmental workflows.

Physics-Conditioned Diffusion Models for Lattice Gauge Theory

We develop diffusion models for simulating lattice gauge theories, where stochastic quantization is explicitly incorporated as a physical condition for sampling. We demonstrate the applicability of this novel sampler to U(1) gauge theory in two spacetime dimensions and find that a model trained at a small inverse coupling constant can be extrapolated to larger inverse coupling regions without encountering the topological freezing problem. Additionally, the trained model can be employed to sample configurations on different lattice sizes without requiring further training. The exactness of the generated samples is ensured by incorporating Metropolis-adjusted Langevin dynamics into the generation process. Furthermore, we demonstrate that this approach enables more efficient sampling of topological quantities compared to traditional algorithms such as Hybrid Monte Carlo and Langevin simulations.

DuoGuard: A Two-Player RL-Driven Framework for Multilingual LLM Guardrails

The rapid advancement of large language models (LLMs) has increased the need for guardrail models to ensure responsible use, particularly in detecting unsafe and illegal content. While substantial safety data exist in English, multilingual guardrail modeling remains underexplored due to the scarcity of open-source safety data in other languages. To address this gap, we propose a novel two-player Reinforcement Learning (RL) framework, where a generator and a guardrail model co-evolve adversarially to produce high-quality synthetic data for multilingual guardrail training. We theoretically formalize this interaction as a two-player game, proving convergence to a Nash equilibrium. Empirical evaluations show that our model \ours outperforms state-of-the-art models, achieving nearly 10% improvement over LlamaGuard3 (8B) on English benchmarks while being 4.5x faster at inference with a significantly smaller model (0.5B). We achieve substantial advancements in multilingual safety tasks, particularly in addressing the imbalance for lower-resource languages in a collected real dataset. Ablation studies emphasize the critical role of synthetic data generation in bridging the imbalance in open-source data between English and other languages. These findings establish a scalable and efficient approach to synthetic data generation, paving the way for improved multilingual guardrail models to enhance LLM safety. Code, model, and data will be open-sourced at https://github.com/yihedeng9/DuoGuard.

Online Robot Motion Planning Methodology Guided by Group Social Proxemics Feature

Nowadays robot is supposed to demonstrate human-like perception, reasoning and behavior pattern in social or service application. However, most of the existing motion planning methods are incompatible with above requirement. A potential reason is that the existing navigation algorithms usually intend to treat people as another kind of obstacle, and hardly take the social principle or awareness into consideration. In this paper, we attempt to model the proxemics of group and blend it into the scenario perception and navigation of robot. For this purpose, a group clustering method considering both social relevance and spatial confidence is introduced. It can enable robot to identify individuals and divide them into groups. Next, we propose defining the individual proxemics within magnetic dipole model, and further established the group proxemics and scenario map through vector-field superposition. On the basis of the group clustering and proxemics modeling, we present the method to obtain the optimal observation positions (OOPs) of group. Once the OOPs grid and scenario map are established, a heuristic path is employed to generate path that guide robot cruising among the groups for interactive purpose. A series of experiments are conducted to validate the proposed methodology on the practical robot, the results have demonstrated that our methodology has achieved promising performance on group recognition accuracy and path-generation efficiency. This concludes that the group awareness evolved as an important module to make robot socially behave in the practical scenario.

DetVPCC: RoI-based Point Cloud Sequence Compression for 3D Object Detection

While MPEG-standardized video-based point cloud compression (VPCC) achieves high compression efficiency for human perception, it struggles with a poor trade-off between bitrate savings and detection accuracy when supporting 3D object detectors. This limitation stems from VPCC's inability to prioritize regions of different importance within point clouds. To address this issue, we propose DetVPCC, a novel method integrating region-of-interest (RoI) encoding with VPCC for efficient point cloud sequence compression while preserving the 3D object detection accuracy. Specifically, we augment VPCC to support RoI-based compression by assigning spatially non-uniform quality levels. Then, we introduce a lightweight RoI detector to identify crucial regions that potentially contain objects. Experiments on the nuScenes dataset demonstrate that our approach significantly improves the detection accuracy. The code and demo video are available in supplementary materials.

A Retrospective Systematic Study on Hierarchical Sparse Query Transformer-assisted Ultrasound Screening for Early Hepatocellular Carcinoma

Hepatocellular carcinoma (HCC) ranks as the third leading cause of cancer-related mortality worldwide, with early detection being crucial for improving patient survival rates. However, early screening for HCC using ultrasound suffers from insufficient sensitivity and is highly dependent on the expertise of radiologists for interpretation. Leveraging the latest advancements in artificial intelligence (AI) in medical imaging, this study proposes an innovative Hierarchical Sparse Query Transformer (HSQformer) model that combines the strengths of Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) to enhance the accuracy of HCC diagnosis in ultrasound screening. The HSQformer leverages sparse latent space representations to capture hierarchical details at various granularities without the need for complex adjustments, and adopts a modular, plug-and-play design philosophy, ensuring the model's versatility and ease of use. The HSQformer's performance was rigorously tested across three distinct clinical scenarios: single-center, multi-center, and high-risk patient testing. In each of these settings, it consistently outperformed existing state-of-the-art models, such as ConvNext and SwinTransformer. Notably, the HSQformer even matched the diagnostic capabilities of senior radiologists and comprehensively surpassed those of junior radiologists. The experimental results from this study strongly demonstrate the effectiveness and clinical potential of AI-assisted tools in HCC screening. The full code is available at https://github.com/Asunatan/HSQformer.

Scalable Higher Resolution Polar Sea Ice Classification and Freeboard Calculation from ICESat-2 ATL03 Data

ICESat-2 (IS2) by NASA is an Earth-observing satellite that measures high-resolution surface elevation. The IS2's ATL07 and ATL10 sea ice elevation and freeboard products of 10m-200m segments which aggregated 150 signal photons from the raw ATL03 (geolocated photon) data. These aggregated products can potentially overestimate local sea surface height, thus underestimating the calculations of freeboard (sea ice height above sea surface). To achieve a higher resolution of sea surface height and freeboard information, in this work we utilize a 2m window to resample the ATL03 data. Then, we classify these 2m segments into thick sea ice, thin ice, and open water using deep learning methods (Long short-term memory and Multi-layer perceptron models). To obtain labeled training data for our deep learning models, we use segmented Sentinel-2 (S2) multi-spectral imagery overlapping with IS2 tracks in space and time to auto-label IS2 data, followed by some manual corrections in the regions of transition between different ice/water types or cloudy regions. We employ a parallel workflow for this auto-labeling using PySpark to scale, and we achieve 9-fold data loading and 16.25-fold map-reduce speedup. To train our models, we employ a Horovod-based distributed deep-learning workflow on a DGX A100 8 GPU cluster, achieving a 7.25-fold speedup. Next, we calculate the local sea surface heights based on the open water segments. Finally, we scale the freeboard calculation using the derived local sea level and achieve 8.54-fold data loading and 15.7-fold map-reduce speedup. Compared with the ATL07 (local sea level) and ATL10 (freeboard) data products, our results show higher resolutions and accuracy (96.56%).