ReSight-SMC: Two-Stage Power Sampling via Island SMC with Visual Scouts

arXiv:2609.34905 · cs.CV · Submitted 2026-09-28 · Read on arXiv

cs.CV

Submitted: 2026-09-28

Updated: 2026-09-28

Code: https://github.com/yaowenzhang1/resight-smc

Terminology

• Benchmark — 38× in this paper · explained in 2 episodes
• Trace — 14× in this paper · explained in 2 episodes
• Aggregation — 13× in this paper · explained in 1 episode
• Ablation — 10× in this paper · explained in 1 episode
• Consistency — 9× in this paper · explained in 3 episodes
• Test-time Scaling — 7× in this paper · explained in 2 episodes
• Verifier — 5× in this paper · explained in 2 episodes
• Accuracy — 4× in this paper · explained in 1 episode
• GRPO — 4× in this paper · explained in 6 episodes
• Self-consistency — 3× in this paper · explained in 2 episodes
• Chain-of-Thought Prompting — 2× in this paper · explained in 2 episodes
• Hallucination — 2× in this paper · explained in 3 episodes
• KV cache — 2× in this paper · explained in 3 episodes
• LLM judge — 2× in this paper · explained in 2 episodes
• Multimodal Reasoning — 2× in this paper · explained in 5 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Degeneracy — 1× in this paper · explained in 3 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Online Adaptation — 1× in this paper · explained in 3 episodes
• Pruning — 1× in this paper · explained in 4 episodes
• Reasoning Traces — 1× in this paper · explained in 3 episodes
• Tokenization — 1× in this paper · explained in 2 episodes

Sources

• Trace: A Taxonomy-Guided Environment for Multidomain Visual Reasoning
• Self-Consistency via Marginal Sharpening
• Power-SMC: Low-Latency Sequence-Level Power Sampling for Training-Free LLM Reasoning
• Qwen3-VL Technical Report
• Qwen2.5-VL Technical Report
• Drift is a Sampling Error: SNR-Aware Power Distributions for Long-Horizon Robotic Planning
• AVIS: Adaptive Test-Time Scaling for Vision-Language Models
• Scalable Power Sampling: Unlocking Efficient, Training-Free Reasoning for LLMs via Distribution Sharpening
• SMCEvolve: Principled Scientific Discovery via Sequential Monte Carlo Evolution
• Aligning Large Vision-Language Models at Test Time: A Trajectory-Guided Structured Sampling Approach
• Reasoning with Sampling: Your Base Model is Smarter Than You Think
• Efficient Test-Time Scaling for Small Vision-Language Models
• MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts
• On Test-Time Scaling for Vision-Language Models
• Power Distribution Bridges Sampling, Self-Reward RL, and Self-Distillation
• Game-RL: Synthesizing Multimodal Verifiable Game Data to Boost VLMs' General Reasoning
• LogicVista: Multimodal LLM Logical Reasoning Benchmark in Visual Contexts
• Reasoning with Sampling: Cutting at Decision Points

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models