test-time-inference

提出 T2Mem 框架，将记忆构建延迟到推理阶段，随推理过程渐进式构建面向查询的记忆，在 LoCoMo 和 LongMemEval 上超越强基线并显著降低记忆构建开销。

提出 In-Distribution Forcing (ID-Forcing) 测试时框架，通过自缓存机制避免 KV 条目偏离训练分布，从而将短时视频扩散模型扩展到分钟级长视频生成，并显著缓解漂移问题。

This paper introduces Chain-of-Experience (CoE), a framework for continual LLM improvement through iterative test-time interactions with self and environmental feedback, showing consistent gains and lower API costs across multiple domains and models.

The paper introduces J64 and R64, interpretable readout methods for reasoning-states in mixture-of-experts AI models, to enhance test-time decision-making and accuracy.

Proposes RT, a test-time inference method that enhances semantic reasoning in text embedding models by running multiple forward passes, improving performance on reasoning tasks while maintaining general semantic understanding.

This paper introduces OCLGen, a compute-efficient test-time search algorithm that integrates generative planning models with a classical Open-Closed List framework, improving solution quality across combinatorial planning domains.