Cover Image

Mela: Test-Time Memory Consolidation based on Transformation Hypothesis

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Chen, Lungchuan
Format:	Preprint
Published:	2026
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Auto-Dreamer: Learning Offline Memory Consolidation for Language Agents
by: Ye, Chongrui, et al.
Published: (2026)

CAMELoT: Towards Large Language Models with Training-Free Consolidated Associative Memory
by: He, Zexue, et al.
Published: (2024)

Testing the Deliteralization Hypothesis in Human and Machine Translation
by: Marmonier, Malik, et al.
Published: (2026)

Memory Retrieval and Consolidation in Large Language Models through Function Tokens
by: Zhang, Shaohua, et al.
Published: (2025)

Statistical Hypothesis Testing for Auditing Robustness in Language Models
by: Rauba, Paulius, et al.
Published: (2025)

RecMem: Recurrence-based Memory Consolidation for Efficient and Effective Long-Running LLM Agents
by: Dai, Zijie, et al.
Published: (2026)

TiMem: Temporal-Hierarchical Memory Consolidation for Long-Horizon Conversational Agents
by: Li, Kai, et al.
Published: (2026)

Parallel Loop Transformer for Efficient Test-Time Computation Scaling
by: Wu, Bohong, et al.
Published: (2025)

Test-Time-Matching: Decouple Personality, Memory, and Linguistic Style in LLM-based Role-Playing Language Agent
by: Zhan, Xiaoyu, et al.
Published: (2025)

Dynamic Cheatsheet: Test-Time Learning with Adaptive Memory
by: Suzgun, Mirac, et al.
Published: (2025)

Algorithm for Automatic Legislative Text Consolidation
by: Etcheverry, Matias, et al.
Published: (2025)

Delving into Multilingual Ethical Bias: The MSQAD with Statistical Hypothesis Tests for Large Language Models
by: Yu, Seunguk, et al.
Published: (2025)

Testing the Machine Consciousness Hypothesis
by: Fitz, Stephen
Published: (2025)

Hypothesis Testing for Quantifying LLM-Human Misalignment in Multiple Choice Settings
by: Hong, Harbin, et al.
Published: (2025)

Why are language models less surprised than humans? Testing the Parse Multiplicity Mismatch Hypothesis
by: Timkey, William, et al.
Published: (2026)

Hypothesis Testing Prompting Improves Deductive Reasoning in Large Language Models
by: Li, Yitian, et al.
Published: (2024)

Time and Memory Trade-off of KV-Cache Compression in Tensor Transformer Decoding
by: Chen, Yifang, et al.
Published: (2025)

EtCon: Edit-then-Consolidate for Reliable Knowledge Editing
by: Li, Ruilin, et al.
Published: (2025)

Memory-Augmented Generative Adversarial Transformers
by: Raaijmakers, Stephan, et al.
Published: (2024)

Estimating the Influence of Sequentially Correlated Literary Properties in Textual Classification: A Data-Centric Hypothesis-Testing Approach
by: Yoffe, Gideon, et al.
Published: (2024)

EdgeInfinite: A Memory-Efficient Infinite-Context Transformer for Edge Devices
by: Chen, Jiyu, et al.
Published: (2025)

Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement
by: Qiu, Linlu, et al.
Published: (2023)

Controllable Text Generation with Residual Memory Transformer
by: Zhang, Hanqing, et al.
Published: (2023)

The Cylindrical Representation Hypothesis for Language Model Steering
by: Gao, Lang, et al.
Published: (2026)

Deep Researcher with Test-Time Diffusion
by: Han, Rujun, et al.
Published: (2025)

Consolidating Rewarded Perturbations for LLM Post-Training
by: Zhang, Zheyu, et al.
Published: (2026)

Consolidating and Developing Benchmarking Datasets for the Nepali Natural Language Understanding Tasks
by: Nyachhyon, Jinu, et al.
Published: (2024)

Attend First, Consolidate Later: On the Importance of Attention in Different LLM Layers
by: Ben-Artzy, Amit, et al.
Published: (2024)

Gated KalmaNet: A Fading Memory Layer Through Test-Time Ridge Regression
by: Peng, Liangzu, et al.
Published: (2025)

TacoMAS: Test-Time Co-Evolution of Topology and Capability in LLM-based Multi-Agent Systems
by: Xu, Chen, et al.
Published: (2026)

MTMT: Consolidating Multiple Thinking Modes to Form a Thought Tree for Strengthening LLM
by: Li, Changcheng, et al.
Published: (2024)

From Hypothesis to Premises: LLM-based Backward Logical Reasoning with Selective Symbolic Translation
by: Li, Qingchuan, et al.
Published: (2025)

Crosscoding Through Time: Tracking Emergence & Consolidation Of Linguistic Representations Throughout LLM Pretraining
by: Bayazit, Deniz, et al.
Published: (2025)

Modeling Grammatical Hypothesis Testing in Young Learners: A Sequence-Based Learning Analytics Study of Morphosyntactic Reasoning in an Interactive Game
by: Geoffre, Thierry, et al.
Published: (2026)

Minerva: A Programmable Memory Test Benchmark for Language Models
by: Xia, Menglin, et al.
Published: (2025)

Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory
by: Wei, Tianxin, et al.
Published: (2025)

Unsupervised Layer-Wise Dynamic Test Time Adaptation for LLMs
by: Xu, Longhuan, et al.
Published: (2026)

DeepSynth-Eval: Objectively Evaluating Information Consolidation in Deep Survey Writing
by: Zhang, Hongzhi, et al.
Published: (2026)

Revisiting the Othello World Model Hypothesis
by: Yuan, Yifei, et al.
Published: (2025)

A Sentiment Consolidation Framework for Meta-Review Generation
by: Li, Miao, et al.
Published: (2024)