Related papers: Tiny Recursive Reasoning with Mamba-2 Attention Hy…
In high-complexity abstract reasoning, a system must infer a latent rule from a few examples or structured observations and apply it to unseen instances. LLMs can express such rules as programs, but ordinary conversation-based refinement is…
Recent advances in deep learning have mainly relied on Transformers due to their data dependency and ability to learn at scale. The attention module in these architectures, however, exhibits quadratic time and space in input size, limiting…
Reasoning models leverage inference-time compute to significantly enhance the performance of language models on difficult logical tasks, and have become a dominating paradigm in frontier LLMs. Despite their wide adoption, the mechanisms…
Large language models (LLMs) have recently shown strong progress on scientific reasoning, yet two major bottlenecks remain. First, explicit retrieval fragments reasoning, imposing a hidden "tool tax" of extra tokens and steps. Second,…
Previous research on lightweight models has primarily focused on CNNs and Transformer-based designs. CNNs, with their local receptive fields, struggle to capture long-range dependencies, while Transformers, despite their global modeling…
Text-to-motion generation, which converts motion language descriptions into coherent 3D human motion sequences, has attracted increasing attention in fields, such as avatar animation and humanoid robotic interaction. Though existing models…
Large language models (LLMs) have been routinely used to solve various tasks using step-by-step reasoning. However, the structure of intermediate reasoning steps, or thoughts, is rigid and unidirectional, such as chains, trees, or…
In real-world reinforcement learning (RL) scenarios, agents often encounter partial observability, where incomplete or noisy information obscures the true state of the environment. Partially Observable Markov Decision Processes (POMDPs) are…
A fundamental objective in robot manipulation is to enable models to comprehend visual scenes and execute actions. Although existing Vision-Language-Action (VLA) models for robots can handle a range of basic tasks, they still face…
Topological deep learning has emerged as a powerful paradigm for modeling higher-order relational structures beyond pairwise interactions that standard graph neural networks fail to capture. While combinatorial complexes (CCs) offer a…
Micro-expressions are typically regarded as unconscious manifestations of a person's genuine emotions. However, their short duration and subtle signals pose significant challenges for downstream recognition. We propose a multi-task learning…
The inference overhead induced by redundant reasoning undermines the interactive experience and severely bottlenecks the deployment of Large Reasoning Models. Existing reinforcement learning (RL)-based solutions tackle this problem by…
Recent studies increasingly explore Large Language Models (LLMs) as a new paradigm for recommendation systems due to their scalability and world knowledge. However, existing work has three key limitations: (1) most efforts focus on…
Radar-based Human Activity Recognition (HAR) is an attractive alternative to wearables and cameras because it preserves privacy, and is contactless and robust to occlusions. However, dominant Convolutional Neural Network (CNN)- and…
Speculative decoding has emerged as a promising approach to accelerating large language model (LLM) generation using a fast drafter while maintaining alignment with the target model's distribution. However, existing approaches face a…
Large language models achieve breakthroughs in complex reasoning via long chain-of-thought sequences. However, this often leads to severe reasoning inflation, causing substantial computational redundancy. To maximize Intelligence per Token,…
Mimicking the real interaction trajectory in the inference of the world model has been shown to improve the sample efficiency of model-based reinforcement learning (MBRL) algorithms. Many methods directly use known state sequences for…
Latent reasoning offers a more efficient alternative to explicit reasoning by compressing intermediate reasoning into continuous representations and substantially shortening reasoning chains. However, existing latent reasoning methods…
In recent years, Transformers-based models have made significant progress in the field of image restoration by leveraging their inherent ability to capture complex contextual features. Recently, Mamba models have made a splash in the field…
State Space Models (SSMs) with selective scan (Mamba) have been adapted into efficient vision models. Mamba, unlike Vision Transformers, achieves linear complexity for token interactions through a recurrent hidden state process. This…