QCVS: Question-Contrastive Visual Steering for Multimodal Reasoning
cs.CV
Submitted: 2026-11-01
Updated: 2026-11-01
Terminology
Sources
- SPARK: Susceptibility-Guided Profiling and Steering of Latent Reasoning States in Large Language Models
- Not All Queries Need Deep Thought: CoFiCot for Adaptive Coarse-to-fine Stateful Refinement
- The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering
- V-ITI: Mitigating Hallucinations in Multimodal Large Language Models via Visual Inference-Time Intervention
- Prefill-Time Intervention for Mitigating Hallucination in Large Vision-Language Models
- Qwen3.5-Omni Technical Report
- DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs