Recent advances in 3D scene reconstruction enable real-time viewing in virtual and augmented as moving or reality editing . To objects, support 3D interacti scene ve inpainting operations methods for better are immersi proposed veness, to repair such or and complete computationally the altered intensi geometry ve optimization, . However making, current them approaches impractical rely for on real-time lengthy or online applications. We propose InstaInpaint, a reference-based feed-forward within framew 0.4 ork seconds.

This work analyzes singular-value spectra of weight matrices in pretrained transformer models to understand how information is stored at both ends of the spectrum.

Designing enzyme backbones with substrate-specific functionality is a critical challenge in computational protein engineering. Current generative models excel in protein design but face limitations in binding data, substrate-specific control, and flexibility for de novo enzyme backbone generation. To address this, we introduce EnzyBind, a dataset with 11,100 experimentally validated enzyme-substrate pairs specifically curated from PDBbind. Building on this, we propose EnzyControl, a method that enables functional and substrate-specific control in enzyme backbone generation. Our approach generates enzyme backbones conditioned on MSAannotated catalytic sites and their corresponding substrates, which are automatically extracted from curated enzyme-substrate data. At the core of EnzyControl is EnzyAdapter, a lightweight, modular component integrated into a pretrained motifscaffolding model, allowing it to become substrate-aware. A two-stage training paradigm further refines the model's ability to generate accurate and functional enzyme structures. Experiments show that our EnzyControl achieves the best performance across structural and functional metrics on EnzyBind and EnzyBench benchmarks, with particularly notable improvements of 13% in designability and 13% in catalytic efficiency compared to the baseline models.

While large language models (LLMs) with Chain-of-Thought (CoT) reasoning excel in mathematics and coding, their potential for systematic reasoning in chemistry, a domain demanding rigorous structural analysis for real-world tasks like drug design and reaction engineering, remains untapped. Current benchmarks focus on simple knowledge retrieval, neglecting step-by-step reasoning required for complex tasks such as molecular optimization and reaction prediction. To address this, we introduce ChemCoTBench, a reasoning framework that bridges molecular structure understanding with arithmetic-inspired operations, including addition, deletion, and substitution, to formalize chemical problem-solving into transparent, step-by-step workflows. By treating molecular transformations as modular "chemical operations", the framework enables slow-thinking reasoning, mirroring the logic of mathematical proofs while grounding solutions in real-world chemical constraints. We evaluate models on two high-impact tasks: Molecular Property Optimization and Chemical Reaction Prediction. These tasks mirror real-world challenges while providing structured evaluability. We further provide ChemCoTDataset, a pioneering 22,000-instance chemical reasoning dataset with expert-annotated chains of thought to facilitate LLM fine-tuning.

Preference-based reinforcement learning (PbRL) has emerged as a promising paradigm for teaching robots complex behaviors without reward engineering. However, its effectiveness is often limited by two critical challenges: the reliance on extensive human input and the inherent difficulties in resolving query ambiguity and credit assignment during reward learning. In this paper, we introduce PRIMT, a PbRL framework designed to overcome these challenges by leveraging foundation models (FMs) for multimodal synthetic feedback and trajectory synthesis. Unlike prior approaches that rely on single-modality FM evaluations, PRIMT employs a hierarchical neuro-symbolic fusion strategy, integrating the complementary strengths of large language models and vision-language models in evaluating robot behaviors for more reliable and comprehensive feedback. PRIMT also incorporates foresight trajectory generation, which reduces early-stage query ambiguity by warm-starting the trajectory buffer with bootstrapped samples, and hindsight trajectory augmentation, which enables counterfactual reasoning with a causal auxiliary loss to improve credit assignment. We evaluate PRIMT on 2 locomotion and 6 manipulation tasks on various benchmarks, demonstrating superior performance over FM-based and scripted baselines.

Human brain achieves dynamic stability-plasticity balance through synaptic homeostasis, a self-regulatory mechanism that stabilizes critical memory traces while preserving optimal learning capacities. Inspired by this biological principle, we propose SPICED: a neuromorphic framework that integrates the synaptic homeostasis mechanism for unsupervised continual EEG decoding, particularly addressing practical scenarios where new individuals with inter-individual variability emerge continually. SPICED comprises a novel synaptic network that enables dynamic expansion during continual adaptation through three bio-inspired neural mechanisms: (1) critical memory reactivation, which mimics brain functional specificity, selectively activates task-relevant memories to facilitate adaptation; (2) synaptic consolidation, which strengthens these reactivated critical memory traces and enhances their replay prioritizations for further adaptations and (3) synaptic renormalization, which are periodically triggered to weaken global memory traces to preserve learning capacities. The interplay within synaptic homeostasis dynamically strengthens task-discriminative memory traces and weakens detrimental memories.

Diffusion Transformers (DiTs) have recently demonstrated remarkable performance in visual generation tasks, surpassing traditional U-Net-based diffusion models by significantly improving image and video generation quality and scalability. However, the large model size and iterative denoising process introduce substantial computational and memory overhead, limiting their deployment in realworld applications. Post-training quantization (PTQ) is a promising solution that compresses models and accelerates inference by converting weights and activations to low-bit representations. Despite its potential, PTQ faces significant challenges when applied to DiTs, often resulting in severe degradation of generative quality. To address these issues, we propose VETA-DiT (Variance-Equalized and Temporal Adaptation for Diffusion Transformers), a dedicated quantization framework for DiTs. Our method first analyzes the sources of quantization error from the perspective of inter-channel variance and introduces a Karhunen-Loève Transform enhanced alignment to equalize variance across channels, facilitating effective quantization under low bit-widths. Furthermore, to handle the temporal variation of activation distributions inherent in the iterative denoising steps of DiTs, we design an incoherence-aware adaptive method that identifies and properly calibrates timesteps with high quantization difficulty.

Large reasoning models (LRMs) have demonstrated strong performance on complex reasoning tasks, but often suffer from overthinking, generating redundant content regardless of task difficulty. Inspired by the dual process theory in cognitive science, we propose Adaptive Cognition Policy Optimization (ACPO), a reinforcement learning framework that enables LRMs to achieve efficient reasoning through adaptive cognitive allocation and dynamic system switch. ACPO incorporates two key components: (1) introducing system-aware reasoning tokens to explicitly represent the thinking modes thereby making the model's cognitive process transparent, and (2) integrating online difficulty estimation and token length budget to guide adaptive system switch and reasoning during reinforcement learning. To this end, we propose a two-stage training strategy. The first stage begins with supervised fine-tuning to cold start the model, enabling it to generate reasoning paths with explicit thinking modes. In the second stage, we apply ACPO to further enhance adaptive system switch for difficulty-aware reasoning. Experimental results demonstrate that ACPO effectively reduces redundant reasoning while adaptively adjusting cognitive allocation based on task complexity, achieving efficient hybrid reasoning.

Reinforcement Learning algorithms commonly sample multiple (n > 1) solution attempts for each problem and reward them independently.