RefineCoder: Iterative Improving of Large Language Models via Adaptive Critique Refinement for Code Generation

Code generation has attracted increasing attention with the rise of Large Language Models (LLMs). Many studies have developed powerful code LLMs by synthesizing code-related instruction data and applying supervised fine-tuning. However, these methods are limited by teacher model distillation and ignore the potential of iterative refinement by self-generated code. In this paper, we propose Adaptive Critique Refinement (ACR), which enables the model to refine itself by self-generated code and external critique, rather than directly imitating the code responses of the teacher model. Concretely, ACR includes a composite scoring system with LLM-as-a-Judge to evaluate the quality of code responses and a selective critique strategy with LLM-as-a-Critic to critique self-generated low-quality code responses. We develop the RefineCoder series by iteratively applying ACR, achieving continuous performance improvement on multiple code generation benchmarks. Compared to the baselines of the same size, our proposed RefineCoder series can achieve comparable or even superior performance using less data.

Robust Watermarks Leak: Channel-Aware Feature Extraction Enables Adversarial Watermark Manipulation

Watermarking plays a key role in the provenance and detection of AI-generated content. While existing methods prioritize robustness against real-world distortions (e.g., JPEG compression and noise addition), we reveal a fundamental tradeoff: such robust watermarks inherently improve the redundancy of detectable patterns encoded into images, creating exploitable information leakage. To leverage this, we propose an attack framework that extracts leakage of watermark patterns through multi-channel feature learning using a pre-trained vision model. Unlike prior works requiring massive data or detector access, our method achieves both forgery and detection evasion with a single watermarked image. Extensive experiments demonstrate that our method achieves a 60\% success rate gain in detection evasion and 51\% improvement in forgery accuracy compared to state-of-the-art methods while maintaining visual fidelity. Our work exposes the robustness-stealthiness paradox: current "robust" watermarks sacrifice security for distortion resistance, providing insights for future watermark design.

Classroom Simulacra: Building Contextual Student Generative Agents in Online Education for Learning Behavioral Simulation

Student simulation supports educators to improve teaching by interacting with virtual students. However, most existing approaches ignore the modulation effects of course materials because of two challenges: the lack of datasets with granularly annotated course materials, and the limitation of existing simulation models in processing extremely long textual data. To solve the challenges, we first run a 6-week education workshop from N = 60 students to collect fine-grained data using a custom built online education system, which logs students' learning behaviors as they interact with lecture materials over time. Second, we propose a transferable iterative reflection (TIR) module that augments both prompting-based and finetuning-based large language models (LLMs) for simulating learning behaviors. Our comprehensive experiments show that TIR enables the LLMs to perform more accurate student simulation than classical deep learning models, even with limited demonstration data. Our TIR approach better captures the granular dynamism of learning performance and inter-student correlations in classrooms, paving the way towards a ''digital twin'' for online education.

Into the Void: Mapping the Unseen Gaps in High Dimensional Data

We present a comprehensive pipeline, augmented by a visual analytics system named ``GapMiner'', that is aimed at exploring and exploiting untapped opportunities within the empty areas of high-dimensional datasets. Our approach begins with an initial dataset and then uses a novel Empty Space Search Algorithm (ESA) to identify the center points of these uncharted voids, which are regarded as reservoirs containing potentially valuable novel configurations. Initially, this process is guided by user interactions facilitated by GapMiner. GapMiner visualizes the Empty Space Configurations (ESC) identified by the search within the context of the data, enabling domain experts to explore and adjust ESCs using a linked parallel-coordinate display. These interactions enhance the dataset and contribute to the iterative training of a connected deep neural network (DNN). As the DNN trains, it gradually assumes the task of identifying high-potential ESCs, diminishing the need for direct user involvement. Ultimately, once the DNN achieves adequate accuracy, it autonomously guides the exploration of optimal configurations by predicting performance and refining configurations, using a combination of gradient ascent and improved empty-space searches. Domain users were actively engaged throughout the development of our system. Our findings demonstrate that our methodology consistently produces substantially superior novel configurations compared to conventional randomization-based methods. We illustrate the effectiveness of our method through several case studies addressing various objectives, including parameter optimization, adversarial learning, and reinforcement learning.

Humanity's Last Exam

Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achieve over 90\% accuracy on popular benchmarks like MMLU, limiting informed measurement of state-of-the-art LLM capabilities. In response, we introduce Humanity's Last Exam (HLE), a multi-modal benchmark at the frontier of human knowledge, designed to be the final closed-ended academic benchmark of its kind with broad subject coverage. HLE consists of 3,000 questions across dozens of subjects, including mathematics, humanities, and the natural sciences. HLE is developed globally by subject-matter experts and consists of multiple-choice and short-answer questions suitable for automated grading. Each question has a known solution that is unambiguous and easily verifiable, but cannot be quickly answered via internet retrieval. State-of-the-art LLMs demonstrate low accuracy and calibration on HLE, highlighting a significant gap between current LLM capabilities and the expert human frontier on closed-ended academic questions. To inform research and policymaking upon a clear understanding of model capabilities, we publicly release HLE at https://lastexam.ai.

Leveraging Large Language Models to Analyze Emotional and Contextual Drivers of Teen Substance Use in Online Discussions

Adolescence is a critical stage often linked to risky behaviors, including substance use, with significant developmental and public health implications. Social media provides a lens into adolescent self-expression, but interpreting emotional and contextual signals remains complex. This study applies Large Language Models (LLMs) to analyze adolescents' social media posts, uncovering emotional patterns (e.g., sadness, guilt, fear, joy) and contextual factors (e.g., family, peers, school) related to substance use. Heatmap and machine learning analyses identified key predictors of substance use-related posts. Negative emotions like sadness and guilt were significantly more frequent in substance use contexts, with guilt acting as a protective factor, while shame and peer influence heightened substance use risk. Joy was more common in non-substance use discussions. Peer influence correlated strongly with sadness, fear, and disgust, while family and school environments aligned with non-substance use. Findings underscore the importance of addressing emotional vulnerabilities and contextual influences, suggesting that collaborative interventions involving families, schools, and communities can reduce risk factors and foster healthier adolescent development.

Training-Free Motion-Guided Video Generation with Enhanced Temporal Consistency Using Motion Consistency Loss

In this paper, we address the challenge of generating temporally consistent videos with motion guidance. While many existing methods depend on additional control modules or inference-time fine-tuning, recent studies suggest that effective motion guidance is achievable without altering the model architecture or requiring extra training. Such approaches offer promising compatibility with various video generation foundation models. However, existing training-free methods often struggle to maintain consistent temporal coherence across frames or to follow guided motion accurately. In this work, we propose a simple yet effective solution that combines an initial-noise-based approach with a novel motion consistency loss, the latter being our key innovation. Specifically, we capture the inter-frame feature correlation patterns of intermediate features from a video diffusion model to represent the motion pattern of the reference video. We then design a motion consistency loss to maintain similar feature correlation patterns in the generated video, using the gradient of this loss in the latent space to guide the generation process for precise motion control. This approach improves temporal consistency across various motion control tasks while preserving the benefits of a training-free setup. Extensive experiments show that our method sets a new standard for efficient, temporally coherent video generation.

Enabling Cardiac Monitoring using In-ear Ballistocardiogram on COTS Wireless Earbuds

The human ear offers a unique opportunity for cardiac monitoring due to its physiological and practical advantages. However, existing earable solutions require additional hardware and complex processing, posing challenges for commercial True Wireless Stereo (TWS) earbuds which are limited by their form factor and resources. In this paper, we propose TWSCardio, a novel system that repurposes the IMU sensors in TWS earbuds for cardiac monitoring. Our key finding is that these sensors can capture in-ear ballistocardiogram (BCG) signals. TWSCardio reuses the unstable Bluetooth channel to stream the IMU data to a smartphone for BCG processing. It incorporates a signal enhancement framework to address issues related to missing data and low sampling rate, while mitigating motion artifacts by fusing multi-axis information. Furthermore, it employs a region-focused signal reconstruction method to translate the multi-axis in-ear BCG signals into fine-grained seismocardiogram (SCG) signals. We have implemented TWSCardio as an efficient real-time app. Our experiments on 100 subjects verify that TWSCardio can accurately reconstruct cardiac signals while showing resilience to motion artifacts, missing data, and low sampling rates. Our case studies further demonstrate that TWSCardio can support diverse cardiac monitoring applications.

Active Sampling and Gaussian Reconstruction for Radio Frequency Radiance Field

Radio-frequency (RF) Radiance Field reconstruction is a challenging problem. The difficulty lies in the interactions between the propagating signal and objects, such as reflections and diffraction, which are hard to model precisely, especially when the shapes and materials of the objects are unknown. Previously, a neural network-based method was proposed to reconstruct the RF Radiance Field, showing promising results. However, this neural network-based method has some limitations: it requires a large number of samples for training and is computationally expensive. Additionally, the neural network only provides the predicted mean of the RF Radiance Field and does not offer an uncertainty model. In this work, we propose a training-free Gaussian reconstruction method for RF Radiance Field. Our method demonstrates that the required number of samples is significantly smaller compared to the neural network-based approach. Furthermore, we introduce an uncertainty model that provides confidence estimates for predictions at any selected position in the scene. We also combine the Gaussian reconstruction method with active sampling, which further reduces the number of samples needed to achieve the same performance. Finally, we explore the potential benefits of our method in a quasi-dynamic setting, showcasing its ability to adapt to changes in the scene without requiring the entire process to be repeated.

Seeing Beyond Views: Multi-View Driving Scene Video Generation with Holistic Attention

Generating multi-view videos for autonomous driving training has recently gained much attention, with the challenge of addressing both cross-view and cross-frame consistency. Existing methods typically apply decoupled attention mechanisms for spatial, temporal, and view dimensions. However, these approaches often struggle to maintain consistency across dimensions, particularly when handling fast-moving objects that appear at different times and viewpoints. In this paper, we present CogDriving, a novel network designed for synthesizing high-quality multi-view driving videos. CogDriving leverages a Diffusion Transformer architecture with holistic-4D attention modules, enabling simultaneous associations across the spatial, temporal, and viewpoint dimensions. We also propose a lightweight controller tailored for CogDriving, i.e., Micro-Controller, which uses only 1.1% of the parameters of the standard ControlNet, enabling precise control over Bird's-Eye-View layouts. To enhance the generation of object instances crucial for autonomous driving, we propose a re-weighted learning objective, dynamically adjusting the learning weights for object instances during training. CogDriving demonstrates strong performance on the nuScenes validation set, achieving an FVD score of 37.8, highlighting its ability to generate realistic driving videos. The project can be found at https://luhannan.github.io/CogDrivingPage/.