Pulmonary embolism (PE) is a leading cause of cardiovascular mortality, yet our understanding of optimal management remains limited due to heterogeneous and inaccessible radiology documentation. The PERT Consortium registry standardizes PE management data but depends on resource-intensive manual abstraction. Large language models (LLMs) offer a scalable alternative for automating concept extraction from computed tomography PE (CTPE) reports. This study evaluated the accuracy of LLMs in extracting PE-related concepts compared to a human-curated criterion standard. We retrospectively analyzed MIMIC-IV and Duke Health CTPE reports using multiple LLaMA models. Larger models (70B) outperformed smaller ones (8B), achieving kappa values of 0.98 (PE detection), 0.65-0.75 (PE location), 0.48-0.51 (right heart strain), and 0.65-0.70 (image artifacts). Moderate temperature tuning (0.2-0.5) improved accuracy, while excessive in-context examples reduced performance. A dual-model review framework achieved >80-90% precision. LLMs demonstrate strong potential for automating PE registry abstraction, minimizing manual workload while preserving accuracy.

DeepSeek-R1-Zero has shown that reinforcement learning (RL) at scale can directly enhance the reasoning capabilities of LLMs without supervised fine-tuning. In this work, we critically examine R1-Zero-like training by analyzing its two core components: base models and RL. We investigate a wide range of base models, including DeepSeek-V3-Base, to understand how pretraining characteristics influence RL performance. Our analysis reveals that DeepSeek-V3-Base already exhibit ''Aha moment'', while Qwen2.5 base models demonstrate strong reasoning capabilities even without prompt templates, suggesting potential pretraining biases. Additionally, we identify an optimization bias in Group Relative Policy Optimization (GRPO), which artificially increases response length (especially for incorrect outputs) during training. To address this, we introduce Dr. GRPO, an unbiased optimization method that improves token efficiency while maintaining reasoning performance. Leveraging these insights, we present a minimalist R1-Zero recipe that achieves 43.3% accuracy on AIME 2024 with a 7B base model, establishing a new state-of-the-art. Our code is available at https://github.com/sail-sg/understand-r1-zero.

Audio Large Language Models (AudioLLMs) have received widespread attention and have significantly improved performance on audio tasks such as conversation, audio understanding, and automatic speech recognition (ASR). Despite these advancements, there is an absence of a benchmark for assessing AudioLLMs in financial scenarios, where audio data, such as earnings conference calls and CEO speeches, are crucial resources for financial analysis and investment decisions. In this paper, we introduce \textsc{FinAudio}, the first benchmark designed to evaluate the capacity of AudioLLMs in the financial domain. We first define three tasks based on the unique characteristics of the financial domain: 1) ASR for short financial audio, 2) ASR for long financial audio, and 3) summarization of long financial audio. Then, we curate two short and two long audio datasets, respectively, and develop a novel dataset for financial audio summarization, comprising the \textsc{FinAudio} benchmark. Then, we evaluate seven prevalent AudioLLMs on \textsc{FinAudio}. Our evaluation reveals the limitations of existing AudioLLMs in the financial domain and offers insights for improving AudioLLMs. All datasets and codes will be released.

Federated Learning (FL) enables distributed ML model training on private user data at the global scale. Despite the potential of FL demonstrated in many domains, an in-depth view of its impact on model accuracy remains unclear. In this paper, we investigate, systematically, how this learning paradigm can affect the accuracy of state-of-the-art ML models for a variety of ML tasks. We present an empirical study that involves various data types: text, image, audio, and video, and FL configuration knobs: data distribution, FL scale, client sampling, and local and global computations. Our experiments are conducted in a unified FL framework to achieve high fidelity, with substantial human efforts and resource investments. Based on the results, we perform a quantitative analysis of the impact of FL, and highlight challenging scenarios where applying FL degrades the accuracy of the model drastically and identify cases where the impact is negligible. The detailed and extensive findings can benefit practical deployments and future development of FL.

In this paper, we introduce zero-shot audio-video editing, a novel task that requires transforming original audio-visual content to align with a specified textual prompt without additional model training. To evaluate this task, we curate a benchmark dataset, AvED-Bench, designed explicitly for zero-shot audio-video editing. AvED-Bench includes 110 videos, each with a 10-second duration, spanning 11 categories from VGGSound. It offers diverse prompts and scenarios that require precise alignment between auditory and visual elements, enabling robust evaluation. We identify limitations in existing zero-shot audio and video editing methods, particularly in synchronization and coherence between modalities, which often result in inconsistent outcomes. To address these challenges, we propose AvED, a zero-shot cross-modal delta denoising framework that leverages audio-video interactions to achieve synchronized and coherent edits. AvED demonstrates superior results on both AvED-Bench and the recent OAVE dataset to validate its generalization capabilities. Results are available at https://genjib.github.io/project_page/AVED/index.html

This study investigates the elicitation of empathy toward a third party through interaction with social agents. Participants engaged with either a physical robot or a voice-enabled chatbot, both driven by a large language model (LLM) programmed to exhibit either an empathetic tone or remain neutral. The interaction is focused on a fictional character, Katie Banks, who is in a challenging situation and in need of financial donations. The willingness to help Katie, measured by the number of hours participants were willing to volunteer, along with their perceptions of the agent, were assessed for 60 participants. Results indicate that neither robotic embodiment nor empathetic tone significantly influenced participants' willingness to volunteer. While the LLM effectively simulated human empathy, fostering genuine empathetic responses in participants proved challenging.

Large language models (LLMs) are designed to align with human values in their responses. This study exploits LLMs with an iterative prompting technique where each prompt is systematically modified and refined across multiple iter ations to enhance its effectiveness in jailbreaking attacks progressively . This technique involves analyzing the response patterns of LLMs, including GPT - 3.5, GPT - 4, LLaMa2, Vicuna, and ChatGLM, allowing us to adjust and optimize prompts to evade the LLMs' ethical and security constraints. Persuasion strategies enhance prompt effectiveness while maintaining consistency with malicious intent. Our results show that the attack success rates (ASR) increase as the attacking prompts become more refined with the h ighest ASR of 90% for GPT4 and ChatGLMa and the lowest ASR of 68% for LLaMa2. Our technique outperforms baseline techniques (PAIR and PAP) in ASR and shows comparable performance with GCG and ArtPrompt.

The rapid advancement of large language models (LLMs) has spurred significant interest in tool learning, where LLMs are augmented with external tools to tackle complex tasks. However, existing tool environments face challenges in balancing stability, scalability, and realness, particularly for benchmarking purposes. To address this problem, we propose MirrorAPI, a novel framework that trains specialized LLMs to accurately simulate real API responses, effectively acting as "mirrors" to tool environments. Using a comprehensive dataset of request-response pairs from 7,000+ APIs, we employ supervised fine-tuning and chain-of-thought reasoning to enhance simulation fidelity. MirrorAPI achieves superior accuracy and stability compared to state-of-the-art methods, as demonstrated by its performance on the newly constructed MirrorAPI-Bench and its integration into StableToolBench.

This paper introduces a theoretical framework for a Transformer-augmented, sectional Mixture-of-Experts (MoE) architecture that aims to enhance computational efficiency while preserving model scalability. Unlike conventional MoE models, which route entire token embeddings to selected experts, our approach portions the embedding dimension itself -- assigning segments of each token's representation to dedicated experts. To combat losses in token representation, we utilize a pre-expert transformer layer to recompute attention across tokens and reduce the sequence length dimensionality. We extend our theory by deriving optimal scaling laws that a non-linear relationship between the number of experts and factors such as model dimensionality, sequence length, and system overhead. These formulations yield closed-form and numerically-solvable expressions for identifying the optimal expert count under given architectural and hardware constraints. As a result, our framework not only provides theoretical bounds for computing efficiency with varying frameworks but also guides practical design choices for scaling large models effectively. While empirical validation is pending, we present a comprehensive experimental road map to evaluate the framework's efficiency, scalability, and practicality in future work.

Process-supervised reward models serve as a fine-grained function that provides detailed step-wise feedback to model responses, facilitating effective selection of reasoning trajectories for complex tasks. Despite its advantages, evaluation on PRMs remains less explored, especially in the multimodal domain. To address this gap, this paper first benchmarks current vision large language models (VLLMs) as two types of reward models: output reward models (ORMs) and process reward models (PRMs) on multiple vision-language benchmarks, which reveal that neither ORM nor PRM consistently outperforms across all tasks, and superior VLLMs do not necessarily yield better rewarding performance. To further advance evaluation, we introduce ViLBench, a vision-language benchmark designed to require intensive process reward signals. Notably, OpenAI's GPT-4o with Chain-of-Thought (CoT) achieves only 27.3% accuracy, indicating the benchmark's challenge for current VLLMs. Lastly, we preliminarily showcase a promising pathway towards bridging the gap between general VLLMs and reward models -- by collecting 73.6K vision-language process reward data using an enhanced tree-search algorithm, our 3B model is able to achieve an average improvement of 3.3% over standard CoT and up to 2.5% compared to its untrained counterpart on ViLBench by selecting OpenAI o1's generations. We release the implementations at https://ucsc-vlaa.github.io/ViLBench with our code, model, and data.