As the default optimizer for training large language models, AdamW has achieved remarkable success in deep learning. However, its convergence behavior is not theoretically well-understood.

We present StreamBridge, a simple yet effective framework that seamlessly transforms offline Video-LLMs into streaming-capable models. It addresses two fundamental challenges in adapting existing models into online scenarios: (1) limited capability for multi-turn real-time understanding, and (2) lack of proactive response mechanisms. Specifically, StreamBridge incorporates (1) a memory buffer combined with a round-decayed compression strategy, supporting long-context multi-turn interactions, and (2) a decoupled, lightweight activation model that can be effortlessly integrated into existing Video-LLMs, enabling continuous proactive responses. To further support StreamBridge, we construct Stream-IT, a large-scale dataset tailored for streaming video understanding, featuring interleaved videotext sequences and diverse instruction formats. Extensive experiments show that StreamBridge significantly improves the streaming understanding capabilities of offline Video-LLMs across various tasks, outperforming even proprietary models such as GPT-4o and Gemini 1.5 Pro. Simultaneously, it achieves competitive or superior performance on standard video understanding benchmarks.

Virtual screening (VS) is a critical component of modern drug discovery, yet most existing methods--whether physics-based or deep learning-based--are developed around holo protein structures with known ligand-bound pockets. Consequently, their performance degrades significantly on apo or predicted structures such as those from AlphaFold2, which are more representative of real-world early-stage drug discovery, where pocket information is often missing. In this paper, we introduce an alignment-and-aggregation framework to enable accurate virtual screening under structural uncertainty. Our method comprises two core components: (1) a tri-modal contrastive learning module that aligns representations of the ligand, the holo pocket, and cavities detected from structures, thereby enhancing robustness to pocket localization error; and (2) a cross-attention based adapter for dynamically aggregating candidate binding sites, enabling the model to learn from activity data even without precise pocket annotations. We evaluated our method on a newly curated benchmark of apo structures, where it significantly outperforms state-of-the-art methods in blind apo setting, improving the early enrichment factor (EF1%) from 11.75 to 37.19. Notably, it also maintains strong performance on holo structures. These results demonstrate the promise of our approach in advancing firstin-class drug discovery, particularly in scenarios lacking experimentally resolved protein-ligand complexes. Our implementation is publicly available at https: //github.com/Wiley-Z/AANet.

People continuously perceive and interact with their surroundings based on underlying intentions that drive their exploration and behaviors.

Human-in-the-loop (HIL) imitation learning enables agents to learn complex behaviors safely through real-time human intervention. However, existing methods struggle to efficiently leverage agent-generated data due to dynamically evolving trajectory distributions and imperfections caused by human intervention delays, often failing to faithfully imitate the human expert policy. In this work, we propose Faithful Dynamic Imitation Learning (FaithDaIL) to address these challenges. We formulate learning from human intervention as an online non-convex problem and employ dynamic regret minimization to adapt to the shifting data distribution and track high-quality policy trajectories. To ensure faithful imitation of human expert despite training on mixed agent and human data, we introduce an unbiased imitation objective and achieve it by weighting the behavior distribution relative to the human expert's as a proxy reward. Extensive experiments on MetaDrive and CARLA driving benchmarks demonstrate that FaithDaIL achieves state-ofthe-art performance in safety and task success with significantly reduced human intervention data compared to prior HIL baselines.

Dynamic 4DGaussian Splatting (4DGS) effectively extends the high-speed rendering capabilities of 3DGaussian Splatting (3DGS) to represent volumetric videos.

Text-to-image (T2I) generation has made remarkable progress, yet existing systems still lack intuitive control over spatial composition, object consistency, and multistep editing. We present LayerCraft, a modular framework that uses large language models (LLMs) as autonomous agents to orchestrate structured, layered image generation and editing. LayerCraft supports two key capabilities: (1) structured generation from simple prompts via chain-of-thought (CoT) reasoning, enabling it to decompose scenes, reason about object placement, and guide composition in a controllable, interpretable manner; and (2) layered object integration, allowing users to insert and customize objects--such as characters or props--across diverse images or scenes while preserving identity, context, and style. The system comprises a coordinator agent, the ChainArchitect for CoT-driven layout planning, and the Object Integration Network (OIN) for seamless image editing using off-the-shelf T2I models without retraining. Through applications like batch collage editing and narrative scene generation, LayerCraft empowers non-experts to iteratively design, customize, and refine visual content with minimal manual effort.

Reinforcement learning (RL) yields substantial improvements in large language models' (LLMs) downstream task performance and alignment with human values. Surprisingly, such large gains result from updating only a small subnetwork comprising just 5%-30% of the parameters, with the rest effectively unchanged. We refer to this phenomenon as parameter update sparsity induced by RL. It is observed across all 7 widely-used RL algorithms (e.g., PPO, GRPO, DPO) and all 10 LLMs from different families in our experiments. This sparsity occurs without any explicit sparsity-promoting regularizations or architectural constraints.

Dynamic Novel View Synthesis aims to generate photorealistic views of moving subjects from arbitrary viewpoints. This task is particularly challenging when relying on monocular video, where disentangling structure from motion is ill-posed and supervision is scarce. We introduce Video Diffusion-Aware Reconstruction (ViDAR), a novel 4D reconstruction framework that leverages personalised image diffusion models to synthesise pseudo multi-view supervision signals for training a Gaussian splatting representation. By conditioning on scene-specific features, ViDAR recovers fine-grained appearance details while mitigating artefacts introduced by monocular ambiguity. To address the spatio-temporal inconsistency of diffusion-based supervision, we propose a diffusion-aware loss function and a camera pose optimisation strategy that aligns synthetic views with the underlying scene geometry. Experiments on DyCheck, a challenging benchmark with extreme viewpoint variation, show that ViDAR outperforms all state-of-the-art baselines in visual quality and geometric consistency. We further highlight ViDAR's strong improvement over baselines on dynamic regions and provide a new benchmark to compare performance in reconstructing motion-rich parts of the scene.

Finetuning large language models (LLMs) enables user-specific customization but introduces important safety risks: even a few harmful examples can compromise safety alignment. A common mitigation strategy is to update the model more strongly on examples deemed safe, while downweighting or excluding those flagged as unsafe. However, because safety context can shift within a single example, updating the model equally on both harmful and harmless parts of a response is suboptimal -- an atomic treatment we term static safety shaping. In contrast, we propose dynamic safety shaping (DSS), a dynamic shaping framework that uses fine-grained safety signals to reinforce learning from safe segments of a response while suppressing unsafe content. To enable such fine-grained control during finetuning, we introduce a key insight: guardrail models, traditionally used for filtering, can be repurposed to evaluate partial responses, tracking how safety risk evolves throughout the response, segment by segment. This leads to the Safety Trajectory Assessment of Response (STAR), a token-level signal that enables shaping to operate dynamically over the training sequence. Building on this, we present DSS, a DSS method guided by STAR scores that robustly mitigates finetuning risks and delivers substantial safety improvements across diverse threats, datasets, and model families, all without compromising capability on intended tasks. We encourage future safety research to build on dynamic shaping principles for stronger mitigation against evolving finetuning risks.