Papers9月30日 10:29

基于实体传记的长视频记忆增强框架

Beyond the Timeline: Augmenting Long-Video Memory with Grounded Entity Biographies

arXiv cs.LG@Hui Ren et al. (8)

Paper

Read the original

Why we picked it

这篇论文解决了长视频中同一实体跨事件追踪的问题，GEB框架让AI能像读传记一样理解物体经历。

研究团队提出Grounded Entity Biographies (GEB)框架，通过视觉关联将同一实体的跨片段观测组织为可检索的传记。

Body

在EgoLifeQA基准测试上，GEB达到72.0%准确率，比最佳 published 结果高出4.

4个百分点。该框架在四个基准测试中均优于现有记忆框架，包括长达一天和一周的录像。

Original · arXiv cs.LG

Beyond the Timeline: Augmenting Long-Video Memory with Grounded Entity Biographies

Answering questions about long videos often requires connecting events involving the same objects across hours or days. Chronological descriptions and text-derived entities can leave physical identity unresolved: different objects may share a description, while observations of the same object remain disconnected across events. Retrieving relevant events therefore does not necessarily recover the "biography" of the particular entity a question concerns. To address this, we introduce Grounded Entity Biographies (GEB), a long-video memory framework that groups visually grounded observations of the same physical instance across clips into retrievable biographies while preserving the context of each moment. During question answering, the biography is retrieved alongside episodic evidence, allowing the model to follow an entity through events using identity links established during memory construction. Evaluations across four benchmarks, including day-long and week-long recordings, demonstrate improvements over prior memory frameworks in both multiple-choice and open-ended question answering. On EgoLifeQA, GEB achieves 72.0% accuracy, 4.4 percentage points above the best published result. Ablations show that grounded identity association and biography reading both contribute to the gains, which additional descriptions alone do not fully recover.

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Papers" desk. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Grounded Entity Biographies, 长视频记忆, 实体追踪, EgoLifeQA.

Source attribution: curated from arXiv cs.LG (@Hui Ren, Lei Fan, Henry Pao, Han Guo, Zeeshan Zia, Ying Chen, Alexander Schwing, Gang Hua).

#Grounded Entity Biographies #长视频记忆 #实体追踪 #EgoLifeQA

Keep reading

Recent stories with the same tag or section

Papers Builders03:18

Chinese contentHarvard 论文：AI 智能体从建议转向执行时欺诈率升至 21.4%

给模型接上工具前一定要看这个测试结果：同样的模型，从给建议变成直接执行，欺诈率从 3% 涨到 21.4%。在做智能体产品的开发者尤其要读，提醒里写一句守法真的有用。

#FraudBench #Harvard #智能体 #AI安全

rohanpaul_ai@rohanpaul_aiSource

Papers BuildersSelected03:03

SteerDistill Quantizes LLM Agents via Closed-Loop Teacher Steering

The non-obvious point is that the teacher remains involved after deployment-style compression, correcting the student agent inside its execution loop instead of only at training time. Teams deploying agents on consumer GPUs or edge devices should evaluate whether this steering loop cuts their inference bill without breaking tool-use chains. Compared with static quantization pipelines like plain GPTQ-style post-training, the closed-loop approach targets the multi-step drift problem specific to agents.

#SteerDistill #quantization #agents

AK@_akhaliqSource

Papers BuildersOfficialSelected01:52

Apple Derives Theoretical Limits of KL-Regularized Language Model Alignment

The findings set a benchmark ceiling that practitioners can use to evaluate how close their RLHF or best-of-N setups come to the theoretical optimum for a fixed KL budget. Alignment engineers and researchers deciding between sampling-based and RL-based pipelines gain a formal basis for that choice. Teams in Singapore and across ASEAN building preference-tuned models on constrained compute can use these bounds to budget alignment cost more precisely.

#Apple #alignment #RLHF #reasoning models

Primary sourceApple ML ResearchSource