Robust Offline Imitation Learning Through State-level Trajectory Stitching

Imitation learning (IL) has proven effective for enabling robots to acquire visuomotor skills through expert demonstrations. However, traditional IL methods are limited by their reliance on high-quality, often scarce, expert data, and suffer from covariate shift. To address these challenges, recent advances in offline IL have incorporated suboptimal, unlabeled datasets into the training. In this paper, we propose a novel approach to enhance policy learning from mixed-quality offline datasets by leveraging task-relevant trajectory fragments and rich environmental dynamics. Specifically, we introduce a state-based search framework that stitches state-action pairs from imperfect demonstrations, generating more diverse and informative training trajectories. Experimental results on standard IL benchmarks and real-world robotic tasks showcase that our proposed method significantly improves both generalization and performance.

Model Risk Management for Generative AI In Financial Institutions

The success of OpenAI's ChatGPT in 2023 has spurred financial enterprises into exploring Generative AI applications to reduce costs or drive revenue within different lines of businesses in the Financial Industry. While these applications offer strong potential for efficiencies, they introduce new model risks, primarily hallucinations and toxicity. As highly regulated entities, financial enterprises (primarily large US banks) are obligated to enhance their model risk framework with additional testing and controls to ensure safe deployment of such applications. This paper outlines the key aspects for model risk management of generative AI model with a special emphasis on additional practices required in model validation.

MagicComp: Training-free Dual-Phase Refinement for Compositional Video Generation

Text-to-video (T2V) generation has made significant strides with diffusion models. However, existing methods still struggle with accurately binding attributes, determining spatial relationships, and capturing complex action interactions between multiple subjects. To address these limitations, we propose MagicComp, a training-free method that enhances compositional T2V generation through dual-phase refinement. Specifically, (1) During the Conditioning Stage: We introduce the Semantic Anchor Disambiguation to reinforces subject-specific semantics and resolve inter-subject ambiguity by progressively injecting the directional vectors of semantic anchors into original text embedding; (2) During the Denoising Stage: We propose Dynamic Layout Fusion Attention, which integrates grounding priors and model-adaptive spatial perception to flexibly bind subjects to their spatiotemporal regions through masked attention modulation. Furthermore, MagicComp is a model-agnostic and versatile approach, which can be seamlessly integrated into existing T2V architectures. Extensive experiments on T2V-CompBench and VBench demonstrate that MagicComp outperforms state-of-the-art methods, highlighting its potential for applications such as complex prompt-based and trajectory-controllable video generation. Project page: https://hong-yu-zhang.github.io/MagicComp-Page/.

Defense Against Model Stealing Based on Account-Aware Distribution Discrepancy

Malicious users attempt to replicate commercial models functionally at low cost by training a clone model with query responses. It is challenging to timely prevent such model-stealing attacks to achieve strong protection and maintain utility. In this paper, we propose a novel non-parametric detector called Account-aware Distribution Discrepancy (ADD) to recognize queries from malicious users by leveraging account-wise local dependency. We formulate each class as a Multivariate Normal distribution (MVN) in the feature space and measure the malicious score as the sum of weighted class-wise distribution discrepancy. The ADD detector is combined with random-based prediction poisoning to yield a plug-and-play defense module named D-ADD for image classification models. Results of extensive experimental studies show that D-ADD achieves strong defense against different types of attacks with little interference in serving benign users for both soft and hard-label settings.

R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning

Existing Large Reasoning Models (LRMs) have shown the potential of reinforcement learning (RL) to enhance the complex reasoning capabilities of Large Language Models~(LLMs). While they achieve remarkable performance on challenging tasks such as mathematics and coding, they often rely on their internal knowledge to solve problems, which can be inadequate for time-sensitive or knowledge-intensive questions, leading to inaccuracies and hallucinations. To address this, we propose \textbf{R1-Searcher}, a novel two-stage outcome-based RL approach designed to enhance the search capabilities of LLMs. This method allows LLMs to autonomously invoke external search systems to access additional knowledge during the reasoning process. Our framework relies exclusively on RL, without requiring process rewards or distillation for a cold start. % effectively generalizing to out-of-domain datasets and supporting both Base and Instruct models. Our experiments demonstrate that our method significantly outperforms previous strong RAG methods, even when compared to the closed-source GPT-4o-mini.

An Empirical Study on Eliciting and Improving R1-like Reasoning Models

In this report, we present the third technical report on the development of slow-thinking models as part of the STILL project. As the technical pathway becomes clearer, scaling RL training has become a central technique for implementing such reasoning models. We systematically experiment with and document the effects of various factors influencing RL training, conducting experiments on both base models and fine-tuned models. Specifically, we demonstrate that our RL training approach consistently improves the Qwen2.5-32B base models, enhancing both response length and test accuracy. Furthermore, we show that even when a model like DeepSeek-R1-Distill-Qwen-1.5B has already achieved a high performance level, it can be further refined through RL training, reaching an accuracy of 39.33% on AIME 2024. Beyond RL training, we also explore the use of tool manipulation, finding that it significantly boosts the reasoning performance of large reasoning models. This approach achieves a remarkable accuracy of 86.67% with greedy search on AIME 2024, underscoring its effectiveness in enhancing model capabilities. We release our resources at the STILL project website: https://github.com/RUCAIBox/Slow_Thinking_with_LLMs.

Exploring Simple Siamese Network for High-Resolution Video Quality Assessment

In the research of video quality assessment (VQA), two-branch network has emerged as a promising solution. It decouples VQA with separate technical and aesthetic branches to measure the perception of low-level distortions and high-level semantics respectively. However, we argue that while technical and aesthetic perspectives are complementary, the technical perspective itself should be measured in semantic-aware manner. We hypothesize that existing technical branch struggles to perceive the semantics of high-resolution videos, as it is trained on local mini-patches sampled from videos. This issue can be hidden by apparently good results on low-resolution videos, but indeed becomes critical for high-resolution VQA. This work introduces SiamVQA, a simple but effective Siamese network for highre-solution VQA. SiamVQA shares weights between technical and aesthetic branches, enhancing the semantic perception ability of technical branch to facilitate technical-quality representation learning. Furthermore, it integrates a dual cross-attention layer for fusing technical and aesthetic features. SiamVQA achieves state-of-the-art accuracy on high-resolution benchmarks, and competitive results on lower-resolution benchmarks. Codes will be available at: https://github.com/srcn-ivl/SiamVQA

Unified Arbitrary-Time Video Frame Interpolation and Prediction

Video frame interpolation and prediction aim to synthesize frames in-between and subsequent to existing frames, respectively. Despite being closely-related, these two tasks are traditionally studied with different model architectures, or same architecture but individually trained weights. Furthermore, while arbitrary-time interpolation has been extensively studied, the value of arbitrary-time prediction has been largely overlooked. In this work, we present uniVIP - unified arbitrary-time Video Interpolation and Prediction. Technically, we firstly extend an interpolation-only network for arbitrary-time interpolation and prediction, with a special input channel for task (interpolation or prediction) encoding. Then, we show how to train a unified model on common triplet frames. Our uniVIP provides competitive results for video interpolation, and outperforms existing state-of-the-arts for video prediction. Codes will be available at: https://github.com/srcn-ivl/uniVIP

ProAI: Proactive Multi-Agent Conversational AI with Structured Knowledge Base for Psychiatric Diagnosis

Most LLM-driven conversational AI systems operate reactively, responding to user prompts without guiding the interaction. Most LLM-driven conversational AI systems operate reactively, responding to user prompts without guiding the interaction. However, many real-world applications-such as psychiatric diagnosis, consulting, and interviews-require AI to take a proactive role, asking the right questions and steering conversations toward specific objectives. Using mental health differential diagnosis as an application context, we introduce ProAI, a goal-oriented, proactive conversational AI framework. ProAI integrates structured knowledge-guided memory, multi-agent proactive reasoning, and a multi-faceted evaluation strategy, enabling LLMs to engage in clinician-style diagnostic reasoning rather than simple response generation. Through simulated patient interactions, user experience assessment, and professional clinical validation, we demonstrate that ProAI achieves up to 83.3% accuracy in mental disorder differential diagnosis while maintaining professional and empathetic interaction standards. These results highlight the potential for more reliable, adaptive, and goal-driven AI diagnostic assistants, advancing LLMs beyond reactive dialogue systems.

Pleno-Generation: A Scalable Generative Face Video Compression Framework with Bandwidth Intelligence

Generative model based compact video compression is typically operated within a relative narrow range of bitrates, and often with an emphasis on ultra-low rate applications. There has been an increasing consensus in the video communication industry that full bitrate coverage should be enabled by generative coding. However, this is an extremely difficult task, largely because generation and compression, although related, have distinct goals and trade-offs. The proposed Pleno-Generation (PGen) framework distinguishes itself through its exceptional capabilities in ensuring the robustness of video coding by utilizing a wider range of bandwidth for generation via bandwidth intelligence. In particular, we initiate our research of PGen with face video coding, and PGen offers a paradigm shift that prioritizes high-fidelity reconstruction over pursuing compact bitstream. The novel PGen framework leverages scalable representation and layered reconstruction for Generative Face Video Compression (GFVC), in an attempt to imbue the bitstream with intelligence in different granularity. Experimental results illustrate that the proposed PGen framework can facilitate existing GFVC algorithms to better deliver high-fidelity and faithful face videos. In addition, the proposed framework can allow a greater space of flexibility for coding applications and show superior RD performance with a much wider bitrate range in terms of various quality evaluations. Moreover, in comparison with the latest Versatile Video Coding (VVC) codec, the proposed scheme achieves competitive Bj{\o}ntegaard-delta-rate savings for perceptual-level evaluations.