Related papers: Adaptive Visual Autoregressive Acceleration via Du…

Multimodal Large Language Models have demonstrated remarkable capabilities in video understanding, yet face prohibitive computational costs and performance degradation from ''context rot'' due to massive visual token redundancy. Existing…

Achieving truly adaptive embodied intelligence requires agents that learn not just by imitating static demonstrations, but by continuously improving through environmental interaction, which is akin to how humans master skills through…

The standard vector autoregressive (VAR) models suffer from overparameterization which is a serious issue for high-dimensional time series data as it restricts the number of variables and lags that can be incorporated into the model.…

Vision Transformers (ViTs) have demonstrated superior performance across a wide range of computer vision tasks. However, structured noise artifacts in their feature maps hinder downstream applications such as segmentation and depth…

When self-adaptive systems encounter changes within their surrounding environments, they enact tactics to perform necessary adaptations. For example, a self-adaptive cloud-based system may have a tactic that initiates additional computing…

Next-Token Prediction (NTP) is a de facto approach for autoregressive (AR) video generation, but it suffers from suboptimal unidirectional dependencies and slow inference speed. In this work, we propose a semi-autoregressive (semi-AR)…

Active Learning (AL) has emerged as a powerful approach for minimizing labeling costs by selectively sampling the most informative data for neural network model development. Effective AL for large-scale vision-language models necessitates…

Many Vision-Language-Action (VLA) models flatten image patches into a 1D token sequence, weakening the 2D spatial cues needed for precise manipulation. We introduce IVRA, a lightweight, training-free method that improves spatial…

Recent advances such as DeepSeek R1-Zero highlight the effectiveness of incentive training, a reinforcement learning paradigm that computes rewards solely based on the final answer part of a language model's output, thereby encouraging the…

Recent Vision-Language-Action (VLA) models show strong generalization capabilities, yet they lack introspective mechanisms for anticipating failures and requesting help from a human supervisor. We present \textbf{INSIGHT}, a learning…

Inference networks of traditional Variational Autoencoders (VAEs) are typically amortized, resulting in relatively inaccurate posterior approximation compared to instance-wise variational optimization. Recent semi-amortized approaches were…

Visual Autoregressive (VAR) modeling approach for image generation proposes autoregressive processing across hierarchical scales, decoding multiple tokens per scale in parallel. This method achieves high-quality generation while…

We present novel techniques to accelerate the convergence of Deep Learning algorithms by conducting low overhead removal of redundant neurons -- apoptosis of neurons -- which do not contribute to model learning, during the training phase…

Reinforcement Learning with Verifiable Rewards (RLVR) has become an effective post-training method for improving the reasoning abilities of Large Language Models (LLMs). However, existing methods mainly apply uniform optimization…

Anomaly detection in time series data is important for applications in finance, healthcare, sensor networks, and industrial monitoring. Traditional methods usually struggle with limited labeled data, high false-positive rates, and…

Vision-Language Large Models (VLMs) have become primary backbone of AI, due to the impressive performance. However, their expensive computation costs, i.e., throughput and delay, impede potentials in real-world scenarios. To achieve…

Visual instruction tuning aims to enable large language models to comprehend the visual world, with a pivotal challenge lying in establishing an effective vision-to-language projection. However, existing methods often grapple with the…

Bayesian Additive Regression Trees (BART) is a powerful statistical model that leverages the strengths of Bayesian inference and regression trees. It has received significant attention for capturing complex non-linear relationships and…

Video understanding is inherently intention-driven-humans naturally focus on relevant frames based on their goals. Recent advancements in multimodal large language models (MLLMs) have enabled flexible query-driven reasoning; however,…

Current Vision-Language-Action (VLA) models rely on fixed computational depth, expending the same amount of compute on simple adjustments and complex multi-step manipulation. While Chain-of-Thought (CoT) prompting enables variable…