Cover Image

Sketch-in-Latents: Eliciting Unified Reasoning in MLLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tong, Jintao, Gu, Jiaqi, Lou, Yujing, Fan, Lubin, Zou, Yixiong, Wu, Yue, Ye, Jieping, Li, Ruixuan
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

SwimBird: Eliciting Switchable Reasoning Mode in Hybrid Autoregressive MLLMs
by: Tong, Jintao, et al.
Published: (2026)

Latent Sketchpad: Sketching Visual Thoughts to Elicit Multimodal Reasoning in MLLMs
by: Zhang, Huanyu, et al.
Published: (2025)

Lightweight Frequency Masker for Cross-Domain Few-Shot Semantic Segmentation
by: Tong, Jintao, et al.
Published: (2024)

HybridGS: Decoupling Transients and Statics with 2D and 3D Gaussian Splatting
by: Lin, Jingyu, et al.
Published: (2024)

PTZ-Calib: Robust Pan-Tilt-Zoom Camera Calibration
by: Guo, Jinhui, et al.
Published: (2025)

Self-Disentanglement and Re-Composition for Cross-Domain Few-Shot Segmentation
by: Tong, Jintao, et al.
Published: (2025)

Learning Neural Volumetric Pose Features for Camera Localization
by: Lin, Jingyu, et al.
Published: (2024)

CC-VQA: Conflict- and Correlation-Aware Method for Mitigating Knowledge Conflict in Knowledge-Based Visual Question Answering
by: Hong, Yuyang, et al.
Published: (2026)

SD-VLM: Spatial Measuring and Understanding with Depth-Encoded Vision-Language Models
by: Chen, Pingyi, et al.
Published: (2025)

Adapter Naturally Serves as Decoupler for Cross-Domain Few-Shot Semantic Segmentation
by: Tong, Jintao, et al.
Published: (2025)

CoL3D: Collaborative Learning of Single-view Depth and Camera Intrinsics for Metric 3D Shape Recovery
by: Zhang, Chenghao, et al.
Published: (2025)

Addressing Exacerbated Attention Sink for Source-Free Cross-Domain Few-Shot Learning
by: Yi, Shuai, et al.
Published: (2026)

Revisiting Continuity of Image Tokens for Cross-domain Few-shot Learning
by: Yi, Shuai, et al.
Published: (2025)

Revisiting Pool-based Prompt Learning for Few-shot Class-incremental Learning
by: Jiang, Yongwei, et al.
Published: (2025)

Reconstruction Target Matters in Masked Image Modeling for Cross-Domain Few-Shot Learning
by: Ma, Ran, et al.
Published: (2024)

Random Registers for Cross-Domain Few-Shot Learning
by: Yi, Shuai, et al.
Published: (2025)

Remedying Target-Domain Astigmatism for Cross-Domain Few-Shot Object Detection
by: Jiang, Yongwei, et al.
Published: (2026)

Improving CLIP Adaptation by Breaking Tail Alignment for Source-Free Cross-Domain Few-Shot Learning
by: Yi, Shuai, et al.
Published: (2026)

Knowledge-based Visual Question Answer with Multimodal Processing, Retrieval and Filtering
by: Hong, Yuyang, et al.
Published: (2025)

SLQ: Bridging Modalities via Shared Latent Queries for Retrieval with Frozen MLLMs
by: Lou, Haoran, et al.
Published: (2026)

The Devil is in Low-Level Features for Cross-Domain Few-Shot Segmentation
by: Liu, Yuhan, et al.
Published: (2025)

Interpretable Cross-Domain Few-Shot Learning with Rectified Target-Domain Local Alignment
by: Zhao, Yaze, et al.
Published: (2026)

Learning Unknowns from Unknowns: Diversified Negative Prototypes Generator for Few-Shot Open-Set Recognition
by: Zhang, Zhenyu, et al.
Published: (2024)

FlowCut: Rethinking Redundancy via Information Flow for Efficient Vision-Language Models
by: Tong, Jintao, et al.
Published: (2025)

VITAL: Visual-Semantic Dual Supervision for Enhanced and Interpretable Latent Reasoning in Medical MLLMs
by: Li, Qiaoru, et al.
Published: (2026)

Re-ranking Reasoning Context with Tree Search Makes Large Vision-Language Models Stronger
by: Yang, Qi, et al.
Published: (2025)

AddressCLIP: Empowering Vision-Language Models for City-wide Image Address Localization
by: Xu, Shixiong, et al.
Published: (2024)

E-VAds: An E-commerce Short Videos Understanding Benchmark for MLLMs
by: Liu, Xianjie, et al.
Published: (2026)

Act Wisely: Cultivating Meta-Cognitive Tool Use in Agentic Multimodal Models
by: Yan, Shilin, et al.
Published: (2026)

Mind the Discriminability Trap in Source-Free Cross-domain Few-shot Learning
by: Zhang, Zhenyu, et al.
Published: (2026)

Flatten Long-Range Loss Landscapes for Cross-Domain Few-Shot Learning
by: Zou, Yixiong, et al.
Published: (2024)

Delve into Base-Novel Confusion: Redundancy Exploration for Few-Shot Class-Incremental Learning
by: Zhou, Haichen, et al.
Published: (2024)

Compositional Few-Shot Class-Incremental Learning
by: Zou, Yixiong, et al.
Published: (2024)

Reviving In-domain Fine-tuning Methods for Source-Free Cross-domain Few-shot Learning
by: Zhao, Yaze, et al.
Published: (2026)

MICM: Rethinking Unsupervised Pretraining for Enhanced Few-shot Learning
by: Zhang, Zhenyu, et al.
Published: (2024)

NoPe-NeRF++: Local-to-Global Optimization of NeRF with No Pose Prior
by: Shi, Dongbo, et al.
Published: (2025)

HiDe: Rethinking The Zoom-IN method in High Resolution MLLMs via Hierarchical Decoupling
by: Liu, Xianjie, et al.
Published: (2025)

Towards Unified Surgical Scene Understanding:Bridging Reasoning and Grounding via MLLMs
by: Huang, Jincai, et al.
Published: (2026)

SophiaVL-R1: Reinforcing MLLMs Reasoning with Thinking Reward
by: Fan, Kaixuan, et al.
Published: (2025)

LLaVA-SP: Enhancing Visual Representation with Visual Spatial Tokens for MLLMs
by: Lou, Haoran, et al.
Published: (2025)