X. Wu

collaborators

4 papers

cs.RO2025

RoVer: Robot Reward Model as Test-Time Verifier for Vision-Language-Action Model

Mingtong Dai, Lingbo Liu, Yongjie Bai +6

Vision-Language-Action (VLA) models have become a prominent paradigm for embodied intelligence, yet further performance improvements typically rely on scaling up training data and…

cs.AI2025

AdvChain: Adversarial Chain-of-Thought Tuning for Robust Safety Alignment of Large Reasoning Models

Zihao Zhu, Xinyu Wu, Gehan Hu +3

Large Reasoning Models (LRMs) have demonstrated remarkable capabilities in complex problem-solving through Chain-of-Thought (CoT) reasoning. However, the multi-step nature of CoT i…

hep-ex2025

Measurements of branching fractions of $D^{0} \to K^{-} 3 π^{+} 2 π^{-}$ , $D^{0} \to K^{-} 2 π^{+} π^{-} 2 π^{0}$ and $D^{+} \to K^{-} 3 π^{+} π^{-} π^{0}$

BESIII Collaboration, M. Ablikim, M. N. Achasov +687

Utilizing $7.9 f b^{- 1}$ of $e^{+} e^{-}$ collision data taken with the BESIII detector at the center-of-mass energy of 3.773 GeV, we report the measurements of absolute branching f…

hep-ex2025

Evidence of doubly OZI-suppressed decay $η_{c} \to ω ϕ$ in the radiative decay $J / ψ \to γ η_{c}$

BESIII Collaboration, M. Ablikim, M. N. Achasov +678

Using a sample of $(10087 \pm 44) \times 1 0^{6}$ $J / ψ$ events collected with the BESIII detector at the BEPCII collider, the first evidence for the doubly OZI-suppressed decay $η_{c}…

RoVer: Robot Reward Model as Test-Time Verifier for Vision-Language-Action Model

AdvChain: Adversarial Chain-of-Thought Tuning for Robust Safety Alignment of Large Reasoning Models

Measurements of branching fractions of D0→K−3π+2π−, D0→K−2π+π−2π0 and D+→K−3π+π−π0

Evidence of doubly OZI-suppressed decay ηc​→ωϕ in the radiative decay J/ψ→γηc​

Measurements of branching fractions of $D^{0} \to K^{-} 3 π^{+} 2 π^{-}$ , $D^{0} \to K^{-} 2 π^{+} π^{-} 2 π^{0}$ and $D^{+} \to K^{-} 3 π^{+} π^{-} π^{0}$

Evidence of doubly OZI-suppressed decay $η_{c} \to ω ϕ$ in the radiative decay $J / ψ \to γ η_{c}$