HoPE: Hybrid of Position Embedding for Length Generalization in Vision-Language Models

• URL: http://arxiv.org/abs/2505.20444v1
• Date: Mon, 26 May 2025 18:37:40 GMT
• Title: HoPE: Hybrid of Position Embedding for Length Generalization in Vision-Language Models
• Authors: Haoran Li, Yingjie Qin, Baoyuan Ou, Lai Xu, Ruiwen Xu,
• Abstract summary: Vision-Language Models (VLMs) have made significant progress in multimodal tasks.<n>However, their performance often deteriorates in long-context scenarios.<n>We propose HoPE, a Hybrid of Position Embedding to improve the long-context capabilities ofVLMs.
• Score: 4.105127179940934
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision-Language Models (VLMs) have made significant progress in multimodal tasks. However, their performance often deteriorates in long-context scenarios, particularly long videos. While Rotary Position Embedding (RoPE) has been widely adopted for length generalization in Large Language Models (LLMs), extending vanilla RoPE to capture the intricate spatial-temporal dependencies in videos remains an unsolved challenge. Existing methods typically allocate different frequencies within RoPE to encode 3D positional information. However, these allocation strategies mainly rely on heuristics, lacking in-depth theoretical analysis. In this paper, we first study how different allocation strategies impact the long-context capabilities of VLMs. Our analysis reveals that current multimodal RoPEs fail to reliably capture semantic similarities over extended contexts. To address this issue, we propose HoPE, a Hybrid of Position Embedding designed to improve the long-context capabilities of VLMs. HoPE introduces a hybrid frequency allocation strategy for reliable semantic modeling over arbitrarily long context, and a dynamic temporal scaling mechanism to facilitate robust learning and flexible inference across diverse context lengths. Extensive experiments across four video benchmarks on long video understanding and retrieval tasks demonstrate that HoPE consistently outperforms existing methods, confirming its effectiveness. Code is available at https://github.com/hrlics/HoPE.

Related papers

• LaMPE: Length-aware Multi-grained Positional Encoding for Adaptive Long-context Scaling Without Training [45.74983991122073]
  Large language models (LLMs) experience significant performance degradation when the input exceeds the pretraining context window.<n>Recent studies mitigate this problem by remapping OOD positions into the in-distribution range with fixed mapping strategies.<n>We propose Length-aware Multi-grained Positional Scaling (LaMPE), a training-free method that fully utilizes the model's effective context window.
  arXiv  Detail & Related papers  (2025-08-04T11:22:13Z)
• Universal Video Temporal Grounding with Generative Multi-modal Large Language Models [59.781211641591405]
  This paper presents a computational model for universal video temporal grounding, which accurately localizes temporal moments in videos based on natural language queries.<n>We propose UniTime, a robust and universal video grounding model leveraging the strong vision-language understanding capabilities of generative Multi-modal Large Language Models (MLLMs)<n>Our model effectively handles videos of diverse views, genres, and lengths while comprehending complex language queries.
  arXiv  Detail & Related papers  (2025-06-23T17:53:18Z)
• ViaRL: Adaptive Temporal Grounding via Visual Iterated Amplification Reinforcement Learning [68.76048244253582]
  We introduce ViaRL, the first framework to leverage rule-based reinforcement learning (RL) for optimizing frame selection in video understanding.<n>ViaRL utilizes the answer accuracy of a downstream model as a reward signal to train a frame selector through trial-and-error.<n>ViaRL consistently delivers superior temporal grounding performance and robust generalization across diverse video understanding tasks.
  arXiv  Detail & Related papers  (2025-05-21T12:29:40Z)
• VRoPE: Rotary Position Embedding for Video Large Language Models [13.495442349395287]
  Position Embedding (RoPE) has shown strong performance in text-based Large Language Models (LLMs)<n>Video adaptations, such as RoPE-3D, attempt to encode spatial and temporal dimensions separately but suffer from two major limitations.<n>We propose Position Rotary Embedding (VRoPE), a novel positional encoding method tailored for Video-LLMs.
  arXiv  Detail & Related papers  (2025-02-17T10:53:57Z)
• VideoRoPE: What Makes for Good Video Rotary Position Embedding? [109.88966080843608]
  VideoRoPE consistently surpasses previous RoPE variants, across diverse downstream tasks such as long video retrieval, video understanding, and video hallucination.<n>VideoRoPE features textlow-frequency temporal allocation to mitigate periodic oscillations, a textitdiagonal layout to maintain spatial symmetry, and textadjustable temporal spacing to decouple temporal and spatial indexing.
  arXiv  Detail & Related papers  (2025-02-07T18:56:04Z)
• InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions [104.90258030688256]
  This project introduces disentangled streaming perception, reasoning, and memory mechanisms, enabling real-time interaction with streaming video and audio input.<n>This project simulates human-like cognition, enabling multimodal large language models to provide continuous and adaptive service over time.
  arXiv  Detail & Related papers  (2024-12-12T18:58:30Z)
• What is Wrong with Perplexity for Long-context Language Modeling? [71.34933096461124]
  Long-context inputs are crucial for large language models (LLMs) in tasks such as extended conversations, document summarization, and many-shot in-context learning.<n>Perplexity (PPL) has proven unreliable for assessing long-context capabilities.<n>We propose bfLongPPL, a novel metric that focuses on key tokens by employing a long-short context contrastive method to identify them.
  arXiv  Detail & Related papers  (2024-10-31T09:39:28Z)
• HoPE: A Novel Positional Encoding Without Long-Term Decay for Enhanced Context Awareness and Extrapolation [19.42279057349193]
  positional encodings (PEs) are designed to exhibit long-term decay, based on an entrenched and long-standing inductive opinion.<n>We argue that long-term decay is outdated in the era of LLMs, as LLMs are now applied to tasks demanding precise retrieval of in-context information.
  arXiv  Detail & Related papers  (2024-10-28T17:01:52Z)
• Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA [71.04146366608904]
  Long-context modeling capabilities have garnered widespread attention, leading to the emergence of Large Language Models (LLMs) with ultra-context windows. We propose a novel long-context benchmark, Loong, aligning with realistic scenarios through extended multi-document question answering (QA) Loong introduces four types of tasks with a range of context lengths: Spotlight Locating, Comparison, Clustering, and Chain of Reasoning.
  arXiv  Detail & Related papers  (2024-06-25T09:42:56Z)
• Resonance RoPE: Improving Context Length Generalization of Large Language Models [37.749813693281254]
  This paper addresses the challenge of train-short-test-long (TSTL) scenarios in Large Language Models (LLMs) equipped with Rotary Position Embedding (RoPE) We introduce Resonance RoPE, a novel approach designed to narrow the generalization gap in TSTL scenarios. We present PosGen, a new synthetic benchmark specifically designed for fine-grained behavior analysis in TSTL scenarios.
  arXiv  Detail & Related papers  (2024-02-29T19:02:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.