arXiv subjects

Suhang Li

Publications and source records attributed to Suhang Li.

3 recordsLinked to original sources

arXiv2026

CFCamo: A Counterfactual Detect-or-Abstain Framework for Camouflaged Object Detection

Vision-language reinforcement learning has recently shown strong target-present localization for camouflaged object detection (COD). Yet localization is only one side of the decision: when the agent faces an ordinary image with no camouflaged target, will it still claim that a camouflaged object exists? Standard COD training and evaluation data are positive-only, so agents optimized under this setting can acquire an over-detect bias, a task-specific form of object hallucination that standard COD evaluation leaves unmeasured. To quantify this target-absent behavior, we construct Counterfactual COD (CF-COD), a paired benchmark that removes the camouflaged target from each held-out COD evaluation image while preserving a plausible background. CF-COD evaluates whether a model detects the target on the original image and abstains on the target-absent counterfactual, summarized by Pair Accuracy (PA). We further introduce CFCamo, a paired counterfactual framework for COD with abstention. For training, CFCamo optimizes a Qwen3-VL-4B-Instruct agent with Counterfactual Sequence Policy Optimization (CSPO), which samples paired original-counterfactual rollouts and uses a Counterfactual Paired Reward (CPR) to couple original-image detection with counterfactual abstention. On CAMO-test, CFCamo improves S_alpha by +3.7 pp over the prior RL-based COD baseline; across CF-COD, it reaches 80.0-90.8% PA. Ablations show that removing counterfactual coupling reduces PA to 1.4-5.2% despite strong target-present COD scores, showing that target-present evaluation alone does not characterize detect-or-abstain behavior. Overall, these results indicate that CFCamo improves COD agents by coupling target-present detection with target-absent abstention, rather than merely strengthening target-present localization. Code and data are available at https://github.com/suhang2000/CFCamo.

cs.CV↗

arXiv2026

Coordination Engineering of Dual-Atom Catalysts for Overall Water Splitting: Mechanistic Insights from Constant-Potential First-Principles and Machine Learning

The rational design of bifunctional electrocatalysts for the hydrogen evolution reaction (HER) and oxygen evolution reaction (OER) is essential for achieving efficient and cost-effective overall water splitting. Atomically dispersed transition-metal catalysts, including single-atom catalysts and dual-atom catalysts (DACs), have emerged as a prominent class of heterogeneous catalysts, in which coordination engineering plays a decisive role in tuning catalytic performance. Herein, we explore coordination-engineered bifunctional overall water splitting electrocatalysts using graphene-supported DACs (TM1TM2-C6-xNx) as model systems. By tuning C/N coordination and dual-metal combinations (Fe, Co, Ni, and Cu), a library of 228 structures was constructed. A three-step screening strategy, combining constant-charge and constant-potential density functional theory with kinetic analysis of proton-coupled electron transfer (PCET), identifies 24 highly active candidates (TM1TM2 = CoNi, CoCu and Co2) with mixed C/N coordination for OER. These catalysts exhibit overpotentials comparable to that of IrO2 and low PCET barriers (lower than 0.40 eV), among which 22 also show high HER activity. Machine learning reveals clear coordination-dependent structure-performance relationships. Such bifunctionality arises from coordination engineering that enables the simultaneous optimization of OER intermediate adsorption and the hydrogen binding strength for HER. This work establishes coordination engineering as an effective strategy for designing high-performance bifunctional dual-atom electrocatalysts for overall water splitting.

cond-mat.mtrl-sci↗

arXiv2026

Potential-Induced Dynamic Coordination of Nonmetal Atoms Directly Bound to Metal Centers in Graphene-Embedded Single-Atom Catalysts and Its Implications

Electrode-potential-induced dynamic coordination is an essential factor governing the performance of graphene-embedded single-atom catalysts (SACs). While previous studies have primarily centered on structural dynamics at the metal site, the response of its coordinated nonmetal atoms remains largely unexplored. Here, using Ni SACs with mixed nitrogen/carbon coordination (NiN4-xCx) as representatives, we investigate potential-driven hydrogenation of metal-center-coordinated nonmetallic atoms through constant-potential density functional theory and ab initio molecular dynamics. We find that the C sites directly bound to Ni undergo potential-driven hydrogenation, whereas hydrogenation at N sites is thermodynamically unfavorable. Taking NiNC3 as a representative system, we demonstrate that these hydrogenation processes proceed with accessible kinetic barriers and obey the Br{\o}nsted-Evans-Polanyi relation. The resulting dynamic coordination reshapes the Ni 3d and dz2 orbitals, modulates the stability of the active center, and weakens molecular adsorption through combined electronic and steric effects. These findings reveal that electrode potential and solvent not only regulate the metal center but also dynamically reconfigure its coordination environment, offering novel mechanistic insights into potential-induced coordination dynamics and guiding the rational design of coordination-engineered SACs.

cond-mat.mtrl-sci↗