Skip to main content
Search

North China Electric Power University

4 related articles

Subscribe to updates
  1. When rain and blur degrade the camera, the fusion layer learns to trust it less: 1.41 mAP gain on nuScenes rain

    Camera–LiDAR bird's-eye-view fusion can mistake corrupted visual texture for useful evidence when the camera stream degrades. DARFusion recasts fusion as modality trust estimation: learned reliability cues calibrate both feature streams, and calibrated features, task-driven contexts and a compact degradation descriptor derived from camera BEV features decide how much camera evidence to use. It holds 68.4 mAP and 71.5 NDS on the clean nuScenes validation set and beats the reproduced BEVFusion baseline by 1.41 and 1.31 mAP on real rain and night subsets.

  2. arXiv

    Poisoned fine-tuning can be repaired at two layers: harmful score falls from 11.54 to 0.08

    In fine-tuning-as-a-service, malicious fine-tuning can weaken a model's refusal behavior while keeping its downstream task performance. SLDR replaces layer-wise safety diagnostics with a signed sensitivity spectrum, trains a LoRA recovery adapter only on the two layers with the highest and lowest sensitivity, and uses a representation-based maliciousness score at inference to decide when to activate it. On Llama3.1/SST2, the average harmful score drops from 11.54 to 0.08 while downstream accuracy matches undefended fine-tuning, and the harmful score stays near zero up to a poisoning ratio of 0.9.

  3. arXiv

    SkillDRE evolves malicious agent skills through a dual-stage loop of pre-execution scanning and runtime feedback, reaching a 45.28% average attack success rate across four victim models on SkillsBench

    SkillDRE is a fully automated framework that, given a benign task and its associated skills, autonomously constructs and validates a task-conditioned malicious objective and a verifiable judge rule, then holds both fixed while alternating scanner-guided evolution with runtime-defense-guided refinement, forming a closed loop between the pre-execution and runtime stages; on SkillsBench across four victim models it achieves an average attack success rate of 45.28%, exceeding the strongest baseline by 40.3%, while its final submitted skills receive no SkillScan findings and largely preserve benign-task performance.

  4. Rational design of advanced electrocatalysts based on reactivity descriptors for high-performance lithium-sulfur batteries

    This review organizes lithium-sulfur battery catalyst research around the fundamental chemistry of sulfur conversion and its rate-limiting steps, links catalyst modulation strategies to descriptors, groups descriptors into electronic, thermodynamic, and structural categories with their property-performance relationships, and points toward universal descriptors as well as the potential roles of in situ characterization, computational modeling, and artificial intelligence in descriptor construction and the design of highly active catalysts.

You’re all caught up