Reinforcing Multimodal Understanding and Generation with Dual Self-rewards

Building upon large language models (LLMs), recent large multimodal models (LMMs) unify cross-model understanding and generation into a single framework. However, LMMs still struggle to achieve accurate image-text alignment, prone to generating text responses contradicting the visual input or failing to follow the text-to-image prompts. Current solutions require external supervision (e.g., human feedback or reward models) and only address unidirectional tasks-either understanding or generation. In this work, based on the observation that understanding and generation are inverse dual tasks, we introduce a self-supervised dual reward mechanism to reinforce the understanding and generation capabilities of LMMs. Specifically, we sample multiple outputs for a given input in one task domain, then reverse the input-output pairs to compute the dual likelihood of the model as self-rewards for optimization. Extensive experimental results on visual understanding and generation benchmarks demonstrate that our method can effectively enhance the performance of the model without any external supervision, especially achieving remarkable improvements in text-to-image tasks.

VideoReasonBench: Can MLLMs Perform Vision-Centric Complex Video Reasoning?

Recent studies have shown that long chain-of-thought (CoT) reasoning can significantly enhance the performance of large language models (LLMs) on complex tasks. However, this benefit is yet to be demonstrated in the domain of video understanding, since most existing benchmarks lack the reasoning depth required to demonstrate the advantages of extended CoT chains. While recent efforts have proposed benchmarks aimed at video reasoning, the tasks are often knowledge-driven and do not rely heavily on visual content. To bridge this gap, we introduce VideoReasonBench, a benchmark designed to evaluate vision-centric, complex video reasoning. To ensure visual richness and high reasoning complexity, each video in VideoReasonBench depicts a sequence of fine-grained operations on a latent state that is only visible in part of the video. The questions evaluate three escalating levels of video reasoning skills: recalling observed visual information, inferring the content of latent states, and predicting information beyond the video. Under such task setting, models have to precisely recall multiple operations in the video, and perform step-by-step reasoning to get correct final answers for these questions. Using VideoReasonBench, we comprehensively evaluate 18 state-of-the-art multimodal LLMs (MLLMs), finding that most perform poorly on complex video reasoning, e.g., GPT-4o achieves only 6.9% accuracy, while the thinking-enhanced Gemini-2.5-Pro significantly outperforms others with 56.0% accuracy. Our investigations on "test-time scaling" further reveal that extended thinking budget, while offering none or minimal benefits on existing video benchmarks, is essential for improving the performance on VideoReasonBench.

Leveraging Importance Sampling to Detach Alignment Modules from Large Language Models

The widespread adoption of large language models (LLMs) across industries has increased the demand for high-quality and customizable outputs. However, traditional alignment methods often require retraining large pretrained models, making it difficult to quickly adapt and optimize LLMs for diverse applications. To address this limitation, we propose a novel \textit{Residual Alignment Model} (\textit{RAM}) that formalizes the alignment process as a type of importance sampling. In this framework, the unaligned upstream model serves as the proposal distribution, while the alignment process is framed as secondary sampling based on an autoregressive alignment module that acts as an estimator of the importance weights. This design enables a natural detachment of the alignment module from the target aligned model, improving flexibility and scalability. Based on this model, we derive an efficient sequence-level training strategy for the alignment module, which operates independently of the proposal module. Additionally, we develop a resampling algorithm with iterative token-level decoding to address the common first-token latency issue in comparable methods. Experimental evaluations on two leading open-source LLMs across diverse tasks, including instruction following, domain adaptation, and preference optimization, demonstrate that our approach consistently outperforms baseline models.

When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning

Large reasoning models (LRMs) have significantly advanced performance on complex tasks, yet their tendency to overthink introduces inefficiencies. This study investigates the internal mechanisms of reinforcement learning (RL)-trained LRMs when prompted to save thinking, revealing three distinct thinking modes: no thinking (NT), explicit thinking (ET), and implicit thinking (IT). Through comprehensive analysis of confidence in thinking termination, attention from thinking to generation, and attentional focus on input sections, we uncover key factors influencing the reasoning behaviors. We further find that NT reduces output length at the cost of accuracy, while ET and IT maintain accuracy with reduced response length. Our findings expose fundamental inconsistencies in RL-optimized LRMs, necessitating adaptive improvements for reliable efficiency.

FedRE: Robust and Effective Federated Learning with Privacy Preference

Despite Federated Learning (FL) employing gradient aggregation at the server for distributed training to prevent the privacy leakage of raw data, private information can still be divulged through the analysis of uploaded gradients from clients. Substantial efforts have been made to integrate local differential privacy (LDP) into the system to achieve a strict privacy guarantee. However, existing methods fail to take practical issues into account by merely perturbing each sample with the same mechanism while each client may have their own privacy preferences on privacy-sensitive information (PSI), which is not uniformly distributed across the raw data. In such a case, excessive privacy protection from private-insensitive information can additionally introduce unnecessary noise, which may degrade the model performance. In this work, we study the PSI within data and develop FedRE, that can simultaneously achieve robustness and effectiveness benefits with LDP protection. More specifically, we first define PSI with regard to the privacy preferences of each client. Then, we optimize the LDP by allocating less privacy budget to gradients with higher PSI in a layer-wise manner, thus providing a stricter privacy guarantee for PSI. Furthermore, to mitigate the performance degradation caused by LDP, we design a parameter aggregation mechanism based on the distribution of the perturbed information. We conducted experiments with text tamper detection on T-SROIE and DocTamper datasets, and FedRE achieves competitive performance compared to state-of-the-art methods.

StereoINR: Cross-View Geometry Consistent Stereo Super Resolution with Implicit Neural Representation

Stereo image super-resolution (SSR) aims to enhance high-resolution details by leveraging information from stereo image pairs. However, existing stereo super-resolution (SSR) upsampling methods (e.g., pixel shuffle) often overlook cross-view geometric consistency and are limited to fixed-scale upsampling. The key issue is that previous upsampling methods use convolution to independently process deep features of different views, lacking cross-view and non-local information perception, making it difficult to select beneficial information from multi-view scenes adaptively. In this work, we propose Stereo Implicit Neural Representation (StereoINR), which innovatively models stereo image pairs as continuous implicit representations. This continuous representation breaks through the scale limitations, providing a unified solution for arbitrary-scale stereo super-resolution reconstruction of left-right views. Furthermore, by incorporating spatial warping and cross-attention mechanisms, StereoINR enables effective cross-view information fusion and achieves significant improvements in pixel-level geometric consistency. Extensive experiments across multiple datasets show that StereoINR outperforms out-of-training-distribution scale upsampling and matches state-of-the-art SSR methods within training-distribution scales.

RISE: Radius of Influence based Subgraph Extraction for 3D Molecular Graph Explanation

3D Geometric Graph Neural Networks (GNNs) have emerged as transformative tools for modeling molecular data. Despite their predictive power, these models often suffer from limited interpretability, raising concerns for scientific applications that require reliable and transparent insights. While existing methods have primarily focused on explaining molecular substructures in 2D GNNs, the transition to 3D GNNs introduces unique challenges, such as handling the implicit dense edge structures created by a cut-off radius. To tackle this, we introduce a novel explanation method specifically designed for 3D GNNs, which localizes the explanation to the immediate neighborhood of each node within the 3D space. Each node is assigned an radius of influence, defining the localized region within which message passing captures spatial and structural interactions crucial for the model's predictions. This method leverages the spatial and geometric characteristics inherent in 3D graphs. By constraining the subgraph to a localized radius of influence, the approach not only enhances interpretability but also aligns with the physical and structural dependencies typical of 3D graph applications, such as molecular learning.

A Rusty Link in the AI Supply Chain: Detecting Evil Configurations in Model Repositories

Recent advancements in large language models (LLMs) have spurred the development of diverse AI applications from code generation and video editing to text generation; however, AI supply chains such as Hugging Face, which host pretrained models and their associated configuration files contributed by the public, face significant security challenges; in particular, configuration files originally intended to set up models by specifying parameters and initial settings can be exploited to execute unauthorized code, yet research has largely overlooked their security compared to that of the models themselves; in this work, we present the first comprehensive study of malicious configurations on Hugging Face, identifying three attack scenarios (file, website, and repository operations) that expose inherent risks; to address these threats, we introduce CONFIGSCAN, an LLM-based tool that analyzes configuration files in the context of their associated runtime code and critical libraries, effectively detecting suspicious elements with low false positive rates and high accuracy; our extensive evaluation uncovers thousands of suspicious repositories and configuration files, underscoring the urgent need for enhanced security validation in AI model hosting platforms.

GenTorrent: Scaling Large Language Model Serving with An Overley Network

While significant progress has been made in research and development on open-source and cost-efficient large-language models (LLMs), serving scalability remains a critical challenge, particularly for small organizations and individuals seeking to deploy and test their LLM innovations. Inspired by peer-to-peer networks that leverage decentralized overlay nodes to increase throughput and availability, we propose GenTorrent, an LLM serving overlay that harnesses computing resources from decentralized contributors. We identify four key research problems inherent to enabling such a decentralized infrastructure: 1) overlay network organization; 2) LLM communication privacy; 3) overlay forwarding for resource efficiency; and 4) verification of serving quality. This work presents the first systematic study of these fundamental problems in the context of decentralized LLM serving. Evaluation results from a prototype implemented on a set of decentralized nodes demonstrate that GenTorrent achieves a latency reduction of over 50% compared to the baseline design without overlay forwarding. Furthermore, the security features introduce minimal overhead to serving latency and throughput. We believe this work pioneers a new direction for democratizing and scaling future AI serving capabilities.

The Tenth NTIRE 2025 Efficient Super-Resolution Challenge Report

This paper presents a comprehensive review of the NTIRE 2025 Challenge on Single-Image Efficient Super-Resolution (ESR). The challenge aimed to advance the development of deep models that optimize key computational metrics, i.e., runtime, parameters, and FLOPs, while achieving a PSNR of at least 26.90 dB on the $\operatorname{DIV2K\_LSDIR\_valid}$ dataset and 26.99 dB on the $\operatorname{DIV2K\_LSDIR\_test}$ dataset. A robust participation saw \textbf{244} registered entrants, with \textbf{43} teams submitting valid entries. This report meticulously analyzes these methods and results, emphasizing groundbreaking advancements in state-of-the-art single-image ESR techniques. The analysis highlights innovative approaches and establishes benchmarks for future research in the field.