When History Helps and Hurts: Selective History Use across Multimodal Turns

arXiv:2610.11948 · cs.CL · Submitted 2026-10-08 · Read on arXiv

cs.CL

Submitted: 2026-10-08

Updated: 2026-10-08

Project page: https://link-world.github.io/ReTurn

Terminology

• Accuracy — 54× in this paper · explained in 1 episode
• Benchmark — 19× in this paper · explained in 2 episodes
• Adaptation — 14× in this paper · explained in 1 episode
• Consistency — 6× in this paper · explained in 3 episodes
• Verification — 4× in this paper · explained in 2 episodes
• Provenance — 3× in this paper · explained in 4 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Aggregation — 2× in this paper · explained in 1 episode
• Benchmarking — 2× in this paper · explained in 3 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Regularization — 2× in this paper · explained in 3 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Core — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Tokenization — 1× in this paper · explained in 2 episodes

Sources

• MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction
• LoRA: Low-Rank Adaptation of Large Language Models
• Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence
• Qwen3-Omni Technical Report
• Qwen3-VL Technical Report
• Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity
• InteractiveOmni: A Unified Omni-modal Model for Audio-Visual Multi-turn Dialogue
• InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
• MiMo-Audio: Audio Language Models are Few-Shot Learners
• LLaVA-Video: Video Instruction Tuning With Synthetic Data

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering