RuCL: Stratified Rubric-Based Curriculum Learning for Multimodal Large Language Model Reasoning

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a prevailing paradigm for enhancing reasoning in Multimodal Large Language Models (MLLMs). However, relying solely on outcome supervision risks reward hacking, where models learn spurious reasoning patterns to satisfy final answer checks. While recent rubric-based approaches offer fine-grained supervision signals, they suffer from high computational costs of instance-level generation and inefficient training dynamics caused by treating all rubrics as equally learnable. In this paper, we propose Stratified Rubric-based Curriculum Learning (RuCL), a novel framework that reformulates curriculum learning by shifting the focus from data selection to reward design. RuCL generates generalized rubrics for broad applicability and stratifies them based on the model's competence. By dynamically adjusting rubric weights during training, RuCL guides the model from mastering foundational perception to tackling advanced logical reasoning. Extensive experiments on various visual reasoning benchmarks show that RuCL yields a remarkable +7.83% average improvement over the Qwen2.5-VL-7B model, achieving a state-of-the-art accuracy of 60.06%.

Unifying Stable Optimization and Reference Regularization in RLHF

Reinforcement Learning from Human Feedback (RLHF) has advanced alignment capabilities significantly but remains hindered by two core challenges: \textbf{reward hacking} and \textbf{stable optimization}. Current solutions independently address these issues through separate regularization strategies, specifically a KL-divergence penalty against a supervised fine-tuned model ($π_0$) to mitigate reward hacking, and policy ratio clipping towards the current policy ($π_t$) to promote stable alignment. However, the implicit trade-off arising from simultaneously regularizing towards both $π_0$ and $π_t$ remains under-explored. In this paper, we introduce a unified regularization approach that explicitly balances the objectives of preventing reward hacking and maintaining stable policy updates. Our simple yet principled alignment objective yields a weighted supervised fine-tuning loss with a superior trade-off, which demonstrably improves both alignment results and implementation complexity. Extensive experiments across diverse benchmarks validate that our method consistently outperforms RLHF and online preference learning methods, achieving enhanced alignment performance and stability.

Beyond Quantity: Trajectory Diversity Scaling for Code Agents

As code large language models (LLMs) evolve into tool-interactive agents via the Model Context Protocol (MCP), their generalization is increasingly limited by low-quality synthetic data and the diminishing returns of quantity scaling. Moreover, quantity-centric scaling exhibits an early bottleneck that underutilizes trajectory data. We propose TDScaling, a Trajectory Diversity Scaling-based data synthesis framework for code agents that scales performance through diversity rather than raw volume. Under a fixed training budget, increasing trajectory diversity yields larger gains than adding more trajectories, improving the performance-cost trade-off for agent training. TDScaling integrates four innovations: (1) a Business Cluster mechanism that captures real-service logical dependencies; (2) a blueprint-driven multi-agent paradigm that enforces trajectory coherence; (3) an adaptive evolution mechanism that steers synthesis toward long-tail scenarios using Domain Entropy, Reasoning Mode Entropy, and Cumulative Action Complexity to prevent mode collapse; and (4) a sandboxed code tool that mitigates catastrophic forgetting of intrinsic coding capabilities. Experiments on general tool-use benchmarks (BFCL, tau^2-Bench) and code agent tasks (RebenchT, CodeCI, BIRD) demonstrate a win-win outcome: TDScaling improves both tool-use generalization and inherent coding proficiency. We plan to release the full codebase and the synthesized dataset (including 30,000+ tool clusters) upon publication.

FinCast: A Foundation Model for Financial Time-Series Forecasting

Financial time-series forecasting is critical for maintaining economic stability, guiding informed policymaking, and promoting sustainable investment practices. However, it remains challenging due to various underlying pattern shifts. These shifts arise primarily from three sources: temporal non-stationarity (distribution changes over time), multi-domain diversity (distinct patterns across financial domains such as stocks, commodities, and futures), and varying temporal resolutions (patterns differing across per-second, hourly, daily, or weekly indicators). While recent deep learning methods attempt to address these complexities, they frequently suffer from overfitting and typically require extensive domain-specific fine-tuning. To overcome these limitations, we introduce FinCast, the first foundation model specifically designed for financial time-series forecasting, trained on large-scale financial datasets. Remarkably, FinCast exhibits robust zero-shot performance, effectively capturing diverse patterns without domain-specific fine-tuning. Comprehensive empirical and qualitative evaluations demonstrate that FinCast surpasses existing state-of-the-art methods, highlighting its strong generalization capabilities.

OmniCharacter: Towards Immersive Role-Playing Agents with Seamless Speech-Language Personality Interaction

Role-Playing Agents (RPAs), benefiting from large language models, is an emerging interactive AI system that simulates roles or characters with diverse personalities. However, existing methods primarily focus on mimicking dialogues among roles in textual form, neglecting the role's voice traits (e.g., voice style and emotions) as playing a crucial effect in interaction, which tends to be more immersive experiences in realistic scenarios. Towards this goal, we propose OmniCharacter, a first seamless speech-language personality interaction model to achieve immersive RPAs with low latency. Specifically, OmniCharacter enables agents to consistently exhibit role-specific personality traits and vocal traits throughout the interaction, enabling a mixture of speech and language responses. To align the model with speech-language scenarios, we construct a dataset named OmniCharacter-10K, which involves more distinctive characters (20), richly contextualized multi-round dialogue (10K), and dynamic speech response (135K). Experimental results showcase that our method yields better responses in terms of both content and style compared to existing RPAs and mainstream speech-language models, with a response latency as low as 289ms. Code and dataset are available at https://github.com/AlibabaResearch/DAMO-ConvAI/tree/main/OmniCharacter.

A Survey of 3D Reconstruction with Event Cameras: From Event-based Geometry to Neural 3D Rendering

Event cameras have emerged as promising sensors for 3D reconstruction due to their ability to capture per-pixel brightness changes asynchronously. Unlike conventional frame-based cameras, they produce sparse and temporally rich data streams, which enable more accurate 3D reconstruction and open up the possibility of performing reconstruction in extreme environments such as high-speed motion, low light, or high dynamic range scenes. In this survey, we provide the first comprehensive review focused exclusively on 3D reconstruction using event cameras. The survey categorises existing works into three major types based on input modality - stereo, monocular, and multimodal systems, and further classifies them by reconstruction approach, including geometry-based, deep learning-based, and recent neural rendering techniques such as Neural Radiance Fields and 3D Gaussian Splatting. Methods with a similar research focus were organised chronologically into the most subdivided groups. We also summarise public datasets relevant to event-based 3D reconstruction. Finally, we highlight current research limitations in data availability, evaluation, representation, and dynamic scene handling, and outline promising future research directions. This survey aims to serve as a comprehensive reference and a roadmap for future developments in event-driven 3D reconstruction.

A Survey on Event-driven 3D Reconstruction: Development under Different Categories

Event cameras have gained increasing attention for 3D reconstruction due to their high temporal resolution, low latency, and high dynamic range. They capture per-pixel brightness changes asynchronously, allowing accurate reconstruction under fast motion and challenging lighting conditions. In this survey, we provide a comprehensive review of event-driven 3D reconstruction methods, including stereo, monocular, and multimodal systems. We further categorize recent developments based on geometric, learning-based, and hybrid approaches. Emerging trends, such as neural radiance fields and 3D Gaussian splatting with event data, are also covered. The related works are structured chronologically to illustrate the innovations and progression within the field. To support future research, we also highlight key research gaps and future research directions in dataset, experiment, evaluation, event representation, etc.

AccidentSim: Generating Physically Realistic Vehicle Collision Videos from Real-World Accident Reports

Collecting real-world vehicle accident videos for autonomous driving research is challenging due to their rarity and complexity. While existing driving video generation methods may produce visually realistic videos, they often fail to deliver physically realistic simulations because they lack the capability to generate accurate post-collision trajectories. In this paper, we introduce AccidentSim, a novel framework that generates physically realistic vehicle collision videos by extracting and utilizing the physical clues and contextual information available in real-world vehicle accident reports. Specifically, AccidentSim leverages a reliable physical simulator to replicate post-collision vehicle trajectories from the physical and contextual information in the accident reports and to build a vehicle collision trajectory dataset. This dataset is then used to fine-tune a language model, enabling it to respond to user prompts and predict physically consistent post-collision trajectories across various driving scenarios based on user descriptions. Finally, we employ Neural Radiance Fields (NeRF) to render high-quality backgrounds, merging them with the foreground vehicles that exhibit physically realistic trajectories to generate vehicle collision videos. Experimental results demonstrate that the videos produced by AccidentSim excel in both visual and physical authenticity.

EvAnimate: Event-conditioned Image-to-Video Generation for Human Animation

Conditional human animation transforms a static reference image into a dynamic sequence by applying motion cues such as poses. These motion cues are typically derived from video data but are susceptible to limitations including low temporal resolution, motion blur, overexposure, and inaccuracies under low-light conditions. In contrast, event cameras provide data streams with exceptionally high temporal resolution, a wide dynamic range, and inherent resistance to motion blur and exposure issues. In this work, we propose EvAnimate, a framework that leverages event streams as motion cues to animate static human images. Our approach employs a specialized event representation that transforms asynchronous event streams into 3-channel slices with controllable slicing rates and appropriate slice density, ensuring compatibility with diffusion models. Subsequently, a dual-branch architecture generates high-quality videos by harnessing the inherent motion dynamics of the event streams, thereby enhancing both video quality and temporal consistency. Specialized data augmentation strategies further enhance cross-person generalization. Finally, we establish a new benchmarking, including simulated event data for training and validation, and a real-world event dataset capturing human actions under normal and extreme scenarios. The experiment results demonstrate that EvAnimate achieves high temporal fidelity and robust performance in scenarios where traditional video-derived cues fall short.

Adaptive Backdoor Attacks with Reasonable Constraints on Graph Neural Networks

Recent studies show that graph neural networks (GNNs) are vulnerable to backdoor attacks. Existing backdoor attacks against GNNs use fixed-pattern triggers and lack reasonable trigger constraints, overlooking individual graph characteristics and rendering insufficient evasiveness. To tackle the above issues, we propose ABARC, the first Adaptive Backdoor Attack with Reasonable Constraints, applying to both graph-level and node-level tasks in GNNs. For graph-level tasks, we propose a subgraph backdoor attack independent of the graph's topology. It dynamically selects trigger nodes for each target graph and modifies node features with constraints based on graph similarity, feature range, and feature type. For node-level tasks, our attack begins with an analysis of node features, followed by selecting and modifying trigger features, which are then constrained by node similarity, feature range, and feature type. Furthermore, an adaptive edge-pruning mechanism is designed to reduce the impact of neighbors on target nodes, ensuring a high attack success rate (ASR). Experimental results show that even with reasonable constraints for attack evasiveness, our attack achieves a high ASR while incurring a marginal clean accuracy drop (CAD). When combined with the state-of-the-art defense randomized smoothing (RS) method, our attack maintains an ASR over 94%, surpassing existing attacks by more than 7%.