Related papers: CKT-WAM: Parameter-Efficient Context Knowledge Tra…

Large language models (LLMs) are trained for downstream tasks by updating their parameters (e.g., via RL). However, updating parameters forces them to absorb task-specific information, which can result in catastrophic forgetting and loss of…

Reinforcement Learning enables agents to learn optimal behaviors through interactions with environments. However, real-world environments are typically non-stationary, requiring agents to continuously adapt to new tasks and changing…

Large Multimodal Models (LMMs) have demonstrated impressive performance in short video understanding tasks but face great challenges when applied to long video understanding. In contrast, Large Language Models (LLMs) exhibit outstanding…

This paper presents Large Wireless Model (LWM) -- the world's first foundation model for wireless channels. Designed as a task-agnostic model, LWM generates universal, rich, contextualized channel embeddings (features) that potentially…

Language agents increasingly require persistent worlds in which they can act, remember, and learn. Existing approaches sit at two extremes: conventional web frameworks provide reliable but fixed contexts backed by databases, while fully…

Knowledge tracing (KT) refers to the problem of predicting future learner performance given their past performance in educational applications. Recent developments in KT using flexible deep neural network-based models excel at this task.…

A natural approach for reinforcement learning is to predict future rewards by unrolling a neural network world model, and to backpropagate through the resulting computational graph to learn a policy. However, this method often becomes…

Diffusion Transformers (DiTs) power high-fidelity video world models but remain computationally expensive due to sequential denoising and costly spatio-temporal attention. Training-free feature caching accelerates inference by reusing…

The Cognitive Categorical Transformer (CCT) is a 306M-parameter architecture that augments a pretrained GPT-2 Small backbone with cognitively grounded components derived from category theory and several inspirations from cognitive science.…

Contextualized entity representations learned by state-of-the-art transformer-based language models (TLMs) like BERT, GPT, T5, etc., leverage the attention mechanism to learn the data context from training data corpus. However, these models…

Parameter-efficient fine-tuning approaches have recently garnered a lot of attention. Having considerably lower number of trainable weights, these methods can bring about scalability and computational effectiveness. In this paper, we look…

Multi-Robot and Multi-Agent Systems demonstrate collective (swarm) intelligence through systematic and distributed integration of local behaviors in a group. Agents sharing knowledge about the mission and environment can enhance performance…

Recent works in end-to-end speech-to-text translation (ST) have proposed multi-tasking methods with soft parameter sharing which leverage machine translation (MT) data via secondary encoders that map text inputs to an eventual cross-modal…

Large Language Models (LLMs) have demonstrated exceptional capabilities across diverse natural language processing benchmarks. However, the escalating scale of model parameters imposes prohibitive memory overheads during training,…

Deploying learned control policies in real-world environments poses a fundamental challenge. When system dynamics change unexpectedly, performance degrades until models are retrained on new data. We introduce Reflexive World Models (RWM), a…

This paper presents a reinforcement learning framework that incorporates a Contextual Reward Machine for task-oriented grasping. The Contextual Reward Machine reduces task complexity by decomposing grasping tasks into manageable sub-tasks.…

Most dominant neural machine translation (NMT) models are restricted to make predictions only according to the local context of preceding words in a left-to-right manner. Although many previous studies try to incorporate global information…

Web agents based on large language models have demonstrated promising capability in automating web tasks. However, current web agents struggle to reason out sensible actions due to the limitations of predicting environment changes, and…

Efficient transfer learning methods such as adapter-based methods have shown great success in unimodal models and vision-language models. However, existing methods have two main challenges in fine-tuning multimodal models. Firstly, they are…

Concept Bottleneck Models (CBMs) tackle the opacity of neural architectures by constructing and explaining their predictions using a set of high-level concepts. A special property of these models is that they permit concept interventions,…