Related papers: ELVIS: Ensemble-Calibrated Latent Imagination for …

Embodied Visual Reasoning (EVR) seeks to follow complex, free-form instructions based on egocentric video, enabling semantic understanding and spatiotemporal reasoning in dynamic environments. Despite its promising potential, EVR encounters…

Long-horizon embodied planning underpins embodied AI. To accomplish long-horizon tasks, one of the most feasible ways is to decompose abstract instructions into a sequence of actionable steps. Foundation models still face logical errors and…

Value Iteration Networks (VINs) have emerged as a popular method to incorporate planning algorithms within deep reinforcement learning, enabling performance improvements on tasks requiring long-range reasoning and understanding of…

In complex embodied long-horizon manipulation tasks, effective task decomposition and execution require synergistic integration of textual logical reasoning and visual-spatial imagination to ensure efficient and accurate operation. Current…

Large-scale instance-level training data is scarce, so models are typically trained on domain-specific datasets. Yet in real-world retrieval, they must handle diverse domains, making generalization to unseen data critical. We introduce…

Large Language Models (LLMs) enable intelligent multi-robot collaboration but face fundamental trade-offs: open-loop methods that compile tasks into formal representations for external executors produce sound plans but lack adaptability in…

Recent vision-language-action (VLA) systems have demonstrated strong capabilities in embodied manipulation. However, most existing VLA policies rely on limited observation windows and end-to-end action prediction, which makes them brittle…

Model predictive control (MPC) is a popular control method that has proved effective for robotics, among other fields. MPC performs re-planning at every time step. Re-planning is done with a limited horizon per computational and real-time…

Latent multi-view subspace clustering has been demonstrated to have desirable clustering performance. However, the original latent representation method vertically concatenates the data matrices from multiple views into a single matrix…

The mathematical capabilities of Multi-modal Large Language Models (MLLMs) remain under-explored with three areas to be improved: visual encoding of math diagrams, diagram-language alignment, and chain-of-thought (CoT) reasoning. This draws…

State-of-the-art model-based Reinforcement Learning (RL) approaches either use gradient-free, population-based methods for planning, learned policy networks, or a combination of policy networks and planning. Hybrid approaches that combine…

Real-world robotic agents must act under partial observability and long horizons, where key cues may appear long before they affect decision making. However, most modern approaches rely solely on instantaneous information, without…

Despite the advanced capabilities of Large Vision-Language Models (LVLMs), they frequently suffer from object hallucination. One reason is that visual features and pretrained textual representations often become intertwined in the deeper…

Recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) have empowered large language models (LLMs) to tackle challenging reasoning tasks such as mathematics and programming. Despite its promise, the RLVR paradigm poses…

Multi-modal Large Language Models (MLLMs) demonstrate remarkable success across various vision-language tasks. However, they suffer from visual hallucination, where the generated responses diverge from the provided image. Are MLLMs…

Humans can perform complex tasks with long-term objectives by planning, reasoning, and forecasting outcomes of actions. For embodied agents to achieve similar capabilities, they must gain knowledge of the environment transferable to novel…

The primary challenge of video streaming is to balance high video quality with smooth playback. Traditional codecs are well tuned for this trade-off, yet their inability to use context means they must encode the entire video data and…

Predictive applications of machine learning often rely on small (sub 1 Bn parameter) specialized models tuned to particular domains or modalities. Such models often achieve excellent performance, but lack flexibility. LLMs and VLMs offer…

Multimodal Large Language Models (MLLMs) have achieved notable gains in various tasks by incorporating Chain-of-Thought (CoT) reasoning in language spaces. Recent work extends this direction by leveraging external tools for visual editing,…

Model-based reinforcement learning (MBRL) improves sample efficiency by optimizing policies inside imagined rollouts, but long-horizon planning degrades when model errors compound and imagined trajectories drift off the training manifold.…