Related papers: Diversify, Contextualize, and Adapt: Efficient Ent…

Contextual memory integration remains a high challenge in the development of language models, particularly in tasks that require maintaining coherence over extended sequences. Traditional approaches, such as self-attention mechanisms and…

Increased adaptability of RNN language models leads to improved predictions that benefit many applications. However, current methods do not take full advantage of the RNN structure. We show that the most widely-used approach to adaptation…

Trajectory forecasting is crucial for video surveillance analytics, as it enables the anticipation of future movements for a set of agents, e.g. basketball players engaged in intricate interactions with long-term intentions. Deep generative…

Feature disentanglement of the foreground target objects and the background surrounding context has not been yet fully accomplished. The lack of network interpretability prevents advancing for feature disentanglement and better…

Language prediction is constrained by informational entropy intrinsic to language, such that there exists a limit to how accurate any language model can become and equivalently a lower bound to language compression. The most efficient…

Contextual representation models have achieved great success in improving various downstream tasks. However, these language-model-based encoders are difficult to train due to the large parameter sizes and high computational complexity. By…

The rapid increase in networked systems and data transmission requires advanced data compression solutions to optimize bandwidth utilization and enhance network performance. This study introduces a novel byte-level predictive model using…

While deep neural networks have led to human-level performance on computer vision tasks, they have yet to demonstrate similar gains for holistic scene understanding. In particular, 3D context has been shown to be an extremely important cue…

Solving multi-label recognition (MLR) for images in the low-label regime is a challenging task with many real-world applications. Recent work learns an alignment between textual and visual spaces to compensate for insufficient image labels,…

Current parameter-efficient fine-tuning (PEFT) methods build adapters widely agnostic of the context of downstream task to learn, or the context of important knowledge to maintain. As a result, there is often a performance gap compared to…

While Deep Reinforcement Learning has been widely researched in medical imaging, the training and deployment of these models usually require powerful GPUs. Since imaging environments evolve rapidly and can be generated by edge devices, the…

This paper explores the combination of neural network quantization and entropy coding for memory footprint minimization. Edge deployment of quantized models is hampered by the harsh Pareto frontier of the accuracy-to-bitwidth tradeoff,…

Neural-based image and video codecs are significantly more power-efficient when weights and activations are quantized to low-precision integers. While there are general-purpose techniques for reducing quantization effects, large losses can…

Existing time series tokenization methods predominantly encode a constant number of samples into individual tokens. This inflexible approach can generate excessive tokens for even simple patterns like extended constant values, resulting in…

The dynamic imbalance of the fore-background is a major challenge in video object counting, which is usually caused by the sparsity of target objects. This remains understudied in existing works and often leads to severe…

Speculative decoding accelerates LLM inference but suffers from performance degradation when target models are fine-tuned for specific domains. A naive solution is to retrain draft models for every target model, which is costly and…

Transformer-based entropy models have gained prominence in recent years due to their superior ability to capture long-range dependencies in probability distribution estimation compared to convolution-based methods. However, previous…

This thesis addresses challenges related to data and parameter efficiency in neural language models, with a focus on representation analysis and the introduction of new optimization techniques. The first part examines the properties and…

State-of-the-art neural machine translation models generate a translation from left to right and every step is conditioned on the previously generated tokens. The sequential nature of this generation process causes fundamental latency in…

We propose a multi-reference and adaptive nonlinear transform source-channel coding (MA-NTSCC) system for wireless image semantic transmission to improve rate-distortion (RD) performance by introducing multi-dimensional contexts into the…