Geng Hong
3 papers · 2026–2026 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
Top co-authors
Research topics
Keywords
attention mechanism
(1)
video understanding
(1)
hallucination mitigation
(1)
jailbreak attack
(1)
greedy decoding
(1)
video-language model
(1)
large reasoning model
(1)
concept unlearning
(1)
rotary positional embedding
(1)
safe generation
(1)
text to image
(1)
early termination
(1)
temporal attention collapse
(1)
safety aha moment
(1)
inference-time safeguard
(1)
scaling sampling strategy
(1)
rectified-flow transformer
(1)
Papers
ReasoningGuard: Safeguarding Large Reasoning Models with Inference-time Safety Aha Moments
ACL 2026
SafeRoPE: Risk-specific Head-wise Embedding Rotation for Safe Generation in Rectified Flow Transformers
CVPR 2026
SmartSight: Mitigating Hallucination in Video-LLMs Without Compromising Video Understanding via Temporal Attention Collapse
AAAI 2026