Xiaofeng Wang
Large Language Model (LLM) agents are increasingly used in real-world products, where personalized and context-aware user interactions are essential. A central enabler of such capabilities is the agent's long-term semantic memory system,…
We present DriveGen3D, a novel framework for generating high-quality and highly controllable dynamic 3D driving scenes that addresses critical limitations in existing methodologies. Current approaches to driving scene synthesis either…
Accurate visual state estimation has been a central topic in robotics with a wide range of applications in robot navigation, autonomous driving, and autonomous flight. Recent advances in robot perception have led to significant improvements…
We present the discovery of EP250827b/SN 2025wkm, an X-ray Flash (XRF) discovered by the Einstein Probe (EP), accompanied by a broad-line Type Ic supernova (SN Ic-BL) at $z = 0.1194$. EP250827b possesses a prompt X-ray luminosity of $\sim…
Autonomous LLM agents operate as long-running processes with persistent workspaces, memory files, scheduled task state, and messaging integrations. These features create a new propagation risk: attacker-influenced content can be written…
We develop a framework for the formation of exotic muonic kaon atoms ($K\mu$) in semileptonic $D^{0}$ decays, using the effective weak Hamiltonian, a helicity-based treatment of the leptonic current, and a nonrelativistic bound-state…
The stability of binary mass transfer is a critical problem for binary evolution. We systematically calculate the adiabatic mass-loss model for naked helium stars with masses ranging from 10$M_{\odot}$ to 80$M_{\odot}$ to study the critical…
Inverse Dynamics Models (IDMs) map visual observations to low-level action commands, serving as central components for data labeling and policy execution in embodied AI. However, their performance degrades severely under manipulator…
The extent of envelope stripping in the progenitor stars is directly reflected in the diversity of spectral features observed in stripped-envelope supernovae (SESNe). Through extensive spectral observation and analysis, we aim to clarify…
Although large language models (LLMs) have shown exceptional capabilities across a wide range of tasks, reliable evaluation remains a critical challenge due to data contamination, opaque operation, and subjective preferences. To address…
We present panchromatic observations of the Type Ia supernova (SN Ia) 2023qov, ranging from $\sim$2 weeks before to $\sim$1 year after maximum light. \textit{JWST} near- and mid-infrared spectra at $+$276 and $+$363~days show $\sim$400 K…
Recent advances in robot foundation models trained on large-scale human teleoperation data have enabled robots to perform increasingly complex real-world tasks. However, scaling these systems remains difficult because collecting…
Vision-language-action (VLA) models have advanced robot manipulation through large-scale pretraining, but real-world deployment remains challenging due to partial observability and delayed feedback. Reinforcement learning addresses this via…
Reconstructing non-rigid objects with physical plausibility remains a significant challenge. Existing approaches leverage differentiable rendering for per-scene optimization, recovering geometry and dynamics but requiring expensive tuning…
Large Language Models (LLMs) have shown a high capability in answering questions on a diverse range of topics. However, these models sometimes produce biased, ideologized or incorrect responses, limiting their applications if there is no…
The deployment of lightweight segmentation models on drones for autonomous power line inspection presents a critical challenge: maintaining reliable performance under real-world conditions that differ from training data. Although compact…
Supernova (SN) 2025coe at a distance of $\sim$25 Mpc is the second-closest calcium-strong (CaST) transient. It was discovered at a large projected offset of $\sim$34 kpc from its potential host galaxy NGC 3277. Multiband photometry of SN…
Large language models (LLMs) are increasingly used in software development, generating code that ranges from short snippets to substantial project components. As AI-generated code becomes more common in real-world repositories, it is…
We present optical photometric and spectroscopic observations of the low-luminosity (LL) Type IIP supernova SN\,2024abfl. The distance to its host galaxy is highly uncertain, with independent estimates of $9.5^{+2.3}_{-2.4}$ Mpc and…
Recently, world-action models (WAM) have emerged to bridge vision-language-action (VLA) models and world models, unifying their reasoning and instruction-following capabilities and spatio-temporal world modeling. However, existing WAM…