1

Fast Spatial Memory with Elastic Test-Time Training

Large Chunk Test-Time Training (LaCT) has shown strong performance on long-context 3D reconstruction, but its fully plastic inference-time updates remain vulnerable to catastrophic forgetting and overfitting. As a result, LaCT is typically …

RoboMME: Benchmarking and Understanding Memory for Robotic Generalist Policies

Memory is critical for long-horizon and history-dependent robotic manipulation. Such tasks often involve counting repeated actions or manipulating objects that become temporarily occluded. Recent vision-language-action (VLA) models have begun to …

Sparse Feature Coactivation Reveals Causal Semantic Modules in Large Language Models

We identify semantically coherent, context-consistent network components in large language models (LLMs) using coactivation of sparse autoencoder (SAE) features collected from just a handful of prompts. Focusing on concept-relation prediction tasks, …

The Mechanistic Emergence of Symbol Grounding in Language Models

Symbol grounding (Harnad, 1990) describes how symbols such as words acquire their meanings by connecting to real-world sensorimotor experiences. Recent work has shown preliminary evidence that grounding may emerge in (vision-)language models trained …

SafetyALFRED: Evaluating Safety-Conscious Planning of Multimodal Large Language Models

SafetyALFRED is a benchmark extending ALFRED with six kitchen hazard categories. We evaluate eleven state-of-the-art models from the Qwen, Gemma, and Gemini families on hazard recognition and risk mitigation through embodied planning. Our findings …

4D-LRM: Large Space-Time Reconstruction Model From and To Any View at Any Time

Can we scale 4D pretraining to learn general space-time representations that reconstruct an object from a few views at some times to any view at any time? We provide an affirmative answer with 4D-LRM, the first large-scale 4D reconstruction model …

Benchmarking and Improving LLM Robustness for Personalized Generation

Recent years have witnessed a growing interest in personalizing the responses of large language models (LLMs). While existing evaluations primarily focus on whether a response aligns with a user's preferences, we argue that factuality is an equally …

Proactive Assistant Dialogue Generation from Streaming Egocentric Videos

Recent advances in conversational AI have been substantial, but developing real-time systems for perceptual task guidance remains challenging. These systems must provide interactive, proactive assistance based on streaming visual inputs, yet their …

Transparent and Coherent Procedural Mistake Detection

Procedural mistake detection (PMD) is a challenging problem of classifying whether a human user (observed through egocentric video) has successfully executed a task (specified by a procedural text). Despite significant recent efforts, machine …

VEGGIE: Instructional Editing and Reasoning of Video Concepts with Grounded Generation

Recent video diffusion models have enhanced video editing, but it remains challenging to handle instructional editing and diverse tasks (e.g., adding, removing, changing) within a unified framework. In this paper, we introduce VEGGIE, a Video Editor …