Copertina

Thinking in Frames: How Visual Context and Test-Time Scaling Empower Video Reasoning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Li, Chengzu, Wang, Zanyi, Li, Jiaang, Xu, Yi, Zhou, Han, Zhang, Huanyu, An, Ruichuan, Jiang, Dengyang, An, Zhaochong, Vulić, Ivan, Belongie, Serge, Korhonen, Anna
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Visual Planning: Let's Think Only with Images
di: Xu, Yi, et al.
Pubblicazione: (2025)

Large Language Models are Miscalibrated In-Context Learners
di: Li, Chengzu, et al.
Pubblicazione: (2023)

TopViewRS: Vision-Language Models as Top-View Spatial Reasoners
di: Li, Chengzu, et al.
Pubblicazione: (2024)

Video Understanding: From Geometry and Semantics to Unified Models
di: An, Zhaochong, et al.
Pubblicazione: (2026)

Imagine while Reasoning in Space: Multimodal Visualization-of-Thought
di: Li, Chengzu, et al.
Pubblicazione: (2025)

Self-Augmented In-Context Learning for Unsupervised Word Translation
di: Li, Yaoyiran, et al.
Pubblicazione: (2024)

How Well Do Models Follow Visual Instructions? VIBE: A Systematic Benchmark for Visual Instruction-Driven Image Editing
di: Zhang, Huanyu, et al.
Pubblicazione: (2026)

Deforming Videos to Masks: Flow Matching for Referring Video Segmentation
di: Wang, Zanyi, et al.
Pubblicazione: (2025)

Beyond the Final Layer: Intermediate Representations for Better Multilingual Calibration in Large Language Models
di: Zhou, Ej, et al.
Pubblicazione: (2025)

RAVENEA: A Benchmark for Multimodal Retrieval-Augmented Visual Culture Understanding
di: Li, Jiaang, et al.
Pubblicazione: (2025)

On Bilingual Lexicon Induction with Large Language Models
di: Li, Yaoyiran, et al.
Pubblicazione: (2023)

Quantifying Language Disparities in Multilingual Large Language Models
di: Hu, Songbo, et al.
Pubblicazione: (2025)

Analyzing and Adapting Large Language Models for Few-Shot Multilingual NLU: Are We There Yet?
di: Razumovskaia, Evgeniia, et al.
Pubblicazione: (2024)

11Plus-Bench: Demystifying Multimodal LLM Spatial Reasoning with Cognitive-Inspired Analysis
di: Li, Chengzu, et al.
Pubblicazione: (2025)

Improving Bilingual Lexicon Induction with Cross-Encoder Reranking
di: Li, Yaoyiran, et al.
Pubblicazione: (2022)

Lost in Embeddings: Information Loss in Vision-Language Models
di: Li, Wenyan, et al.
Pubblicazione: (2025)

SQATIN: Supervised Instruction Tuning Meets Question Answering for Improved Dialogue NLU
di: Razumovskaia, Evgeniia, et al.
Pubblicazione: (2023)

Polyglot Teachers: Evaluating Language Models for Multilingual Synthetic Data Generation
di: Miranda, Lester James V., et al.
Pubblicazione: (2026)

Emergent Communication Pretraining for Few-Shot Machine Translation
di: Li, Yaoyiran, et al.
Pubblicazione: (2020)

Generalized Few-shot 3D Point Cloud Segmentation with Vision-Language Model
di: An, Zhaochong, et al.
Pubblicazione: (2025)

Unlocking the Potential of Grounding DINO in Videos: Parameter-Efficient Adaptation for Limited-Data Spatial-Temporal Localization
di: Wang, Zanyi, et al.
Pubblicazione: (2026)

Scaling Sparse Fine-Tuning to Large Language Models
di: Ansell, Alan, et al.
Pubblicazione: (2024)

Multi-Modal Framing Analysis of News
di: Arora, Arnav, et al.
Pubblicazione: (2025)

Agentic Policy Optimization via Instruction-Policy Co-Evolution
di: Zhou, Han, et al.
Pubblicazione: (2025)

AutoPEFT: Automatic Configuration Search for Parameter-Efficient Fine-Tuning
di: Zhou, Han, et al.
Pubblicazione: (2023)

Translation-Enhanced Multilingual Text-to-Image Generation
di: Li, Yaoyiran, et al.
Pubblicazione: (2023)

ChatMotion: A Multimodal Multi-Agent for Human Motion Analysis
di: Li, Lei, et al.
Pubblicazione: (2025)

Evaluation of Cultural Competence of Vision-Language Models
di: Yadav, Srishti, et al.
Pubblicazione: (2025)

DIALIGHT: Lightweight Multilingual Development and Evaluation of Task-Oriented Dialogue Systems with Large Language Models
di: Hu, Songbo, et al.
Pubblicazione: (2024)

Improving Word Translation via Two-Stage Contrastive Learning
di: Li, Yaoyiran, et al.
Pubblicazione: (2022)

VGGRPO: Towards World-Consistent Video Generation with 4D Latent Reward
di: An, Zhaochong, et al.
Pubblicazione: (2026)

Revisiting the Perception-Distortion Trade-off with Spatial-Semantic Guided Super-Resolution
di: Wang, Dan, et al.
Pubblicazione: (2026)

Multimodality Helps Few-shot 3D Point Cloud Semantic Segmentation
di: An, Zhaochong, et al.
Pubblicazione: (2024)

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

Fairer Preferences Elicit Improved Human-Aligned Large Language Model Judgments
di: Zhou, Han, et al.
Pubblicazione: (2024)

MMEarth-Bench: Global Model Adaptation via Multimodal Test-Time Training
di: Gordon, Lucia, et al.
Pubblicazione: (2026)

Rethinking Few-shot 3D Point Cloud Semantic Segmentation
di: An, Zhaochong, et al.
Pubblicazione: (2024)

Donors and Recipients: On Asymmetric Transfer Across Tasks and Languages with Parameter-Efficient Fine-Tuning
di: Dymkiewicz, Kajetan, et al.
Pubblicazione: (2025)

Better Language Models Exhibit Higher Visual Alignment
di: Ruthardt, Jona, et al.
Pubblicazione: (2024)

When Thinking Hurts: Mitigating Visual Forgetting in Video Reasoning via Frame Repetition
di: Sun, Xiaokun, et al.
Pubblicazione: (2026)