Related papers: Time Is a Feature: Exploiting Temporal Dynamics in…

Recent advances such as self-consistency and test-time reinforcement learning (TTRL) improve the reliability of large language models (LLMs) without additional supervision, yet their underlying mechanisms and statistical guarantees remain…

Video large language models (Video-LLMs) can temporally ground language queries and retrieve video moments. Yet, such temporal comprehension capabilities are neither well-studied nor understood. So we conduct a study on prediction…

Neural Text-to-Speech (TTS) systems find broad applications in voice assistants, e-learning, and audiobook creation. The pursuit of modern models, like Diffusion Models (DMs), holds promise for achieving high-fidelity, real-time speech…

Temporal reasoning over long, multi-session dialogues is a critical capability for conversational agents. However, existing works and our pilot study have shown that as dialogue histories grow in length and accumulate noise, current…

While large language model (LLM) agents have demonstrated impressive problem-solving capabilities, they typically operate as static systems, lacking the ability to evolve through lifelong interaction. Existing attempts to bridge this gap…

Continuously learning new tasks using high-level ideas or knowledge is a key capability of humans. In this paper, we propose Lifelong reinforcement learning with Sequential linear temporal logic formulas and Reward Machines (LSRM), which…

This paper addresses the temporal sentence grounding (TSG). Although existing methods have made decent achievements in this task, they not only severely rely on abundant video-query paired data for training, but also easily fail into the…

Detecting psychological stress from speech is critical in high-pressure settings. While prior work has leveraged acoustic features for stress detection, most treat stress as a static label. In this work, we model stress as a temporally…

Large language models (LLMs) are routinely pre-trained on billions of tokens, only to start the process over again once new data becomes available. A much more efficient solution is to continually pre-train these models, saving significant…

Temporal distribution shift (TDS) erodes the long-term accuracy of recommender systems, yet industrial practice still relies on periodic incremental training, which struggles to capture both stable and transient patterns. Existing…

While large language models (LLMs) have rapidly improved their performance on a broad number of tasks, they still often fall short on reasoning tasks. As LLMs become more integrated in diverse real-world tasks, advancing their reasoning…

The performance of Large Language Models (LLMs) degrades from the temporal drift between data used for model training and newer text seen during inference. One understudied avenue of language change causing data drift is the emergence of…

Reinforcement learning (RL) can be used to improve the policy (denoiser) of diffusion large language models (dLLMs), while being hindered by the intractability of the policy likelihood. A dominant and efficient family of methods replaces…

Detecting anomalies in time series data is crucial for finance, healthcare, sensor networks, and industrial monitoring applications. However, time series anomaly detection often suffers from sparse labels, complex temporal patterns, and…

Diffusion models produce high-fidelity speech but are inefficient for real-time use due to long denoising steps and challenges in modeling intonation and rhythm. To improve this, we propose Diffusion Loss-Guided Policy Optimization (DLPO),…

Diffusion large language models (dLLMs) have emerged as a new architecture following auto regressive models. Their denoising process offers a powerful generative advantage, but they present significant challenges in learning and…

Contrastive Decoding (CD) enhances the generation quality of large language models (LLMs) but incurs significant additional computational overhead due to the need for an auxiliary model. Existing internal self-contrastive decoding methods,…

Test-Time Scaling (TTS) has emerged as an effective paradigm for improving the reasoning performance of large language models (LLMs). However, existing methods -- most notably majority voting and heuristic token-level scoring -- treat…

Despite their growing capabilities, language models still frequently reproduce content from their training data, generate repetitive text, and favor common grammatical patterns and vocabulary. A possible cause is the decoding strategy: the…

The iterative and stochastic nature of diffusion models enables test-time scaling, whereby spending additional compute during denoising generates higher-fidelity samples. Increasing the number of denoising steps is the primary scaling axis,…