Related papers: RW-TTT: Batched Serving for Request-Owned Test-Tim…
Test-Time Training (TTT) models context dependencies by adapting part of the model's weights (referred to as fast weights) during inference. This fast weight, akin to recurrent states in RNNs, stores temporary memories of past tokens in the…
Prior work has established Test-Time Training (TTT) as a general framework to further improve a trained model at test time. Before making a prediction on each test instance, the model is first trained on the same instance using a…
Language models (LMs) have shown impressive performance on tasks within their training distribution, but often struggle with structurally novel tasks even when given a small number of in-context task examples. We investigate the…
The static ``train then deploy" paradigm fundamentally limits Large Language Models (LLMs) from dynamically adapting their weights in response to continuous streams of new information inherent in real-world tasks. Test-Time Training (TTT)…
Test-time training (TTT) with KV binding as sequence modeling layer is commonly interpreted as a form of online meta-learning that memorizes a key-value mapping at test time. However, our analysis reveals multiple phenomena that contradict…
Test-Time Compute (TTC) has emerged as a powerful paradigm for enhancing the performance of Large Language Models (LLMs) at inference, leveraging strategies such as Test-Time Training (TTT) and Retrieval-Augmented Generation (RAG). However,…
The emergence of Large Language Models (LLMs) with strong reasoning capabilities marks a significant milestone, unlocking new frontiers in complex problem-solving. However, training these reasoning models, typically using Reinforcement…
Transformers are slow to train on videos due to extremely large numbers of input tokens, even though many video tokens are repeated over time. Existing methods to remove such uninformative tokens either have significant overhead, negating…
Test-Time Training (TTT) is an emerging paradigm that enables models to adapt their parameters during inference, improving performance on tasks such as few-shot learning, retrieval-augmented generation, and complex reasoning. However, this…
The rapid advancements in vision-language models (VLMs), such as CLIP, have intensified the need to address distribution shifts between training and testing datasets. Although prior Test-Time Training (TTT) techniques for VLMs have…
Recurrent neural networks (RNNs) with deep test-time memorization modules, such as Titans and TTT, represent a promising, linearly-scaling paradigm distinct from Transformers. While these expressive models do not yet match the peak…
Test-time training (TTT) enhances model performance by explicitly updating designated parameters prior to each prediction to adapt to the test data. While TTT has demonstrated considerable empirical success, its theoretical underpinnings…
We study Latent Recurrent Transformer (LRT), a lightweight augmentation of autoregressive transformers that reuses a high-level source-layer hidden state from the previous token as recurrent memory for the next token. Because this source…
Test-time training (TTT) methods explicitly update the weights of a model to adapt to the specific test instance, and they have found success in a variety of settings, including most recently language modeling and reasoning. To demystify…
Many applications must provide low-latency LLM service to users or risk unacceptable user experience. However, over-provisioning resources to serve fluctuating request patterns is often prohibitively expensive. In this work, we present a…
Time-series forecasting has seen significant advancements with the introduction of token prediction mechanisms such as multi-head attention. However, these methods often struggle to achieve the same performance as in language modeling,…
Multi-task learning (MTL) seeks to improve the generalized performance of learning specific tasks, exploiting useful information incorporated in related tasks. As a promising area, this paper studies an MTL-based control approach…
Deep learning models have demonstrated exceptional performance across a wide range of computer vision tasks. However, their performance often degrades significantly when faced with distribution shifts, such as domain or dataset changes.…
Graph Neural Networks have demonstrated great success in various fields of multimedia. However, the distribution shift between the training and test data challenges the effectiveness of GNNs. To mitigate this challenge, Test-Time Training…
Generalizing neural networks to unseen target domains is a significant challenge in real-world deployments. Test-time training (TTT) addresses this by using an auxiliary self-supervised task to reduce the domain gap caused by distribution…