Related papers: Disentangling MLP Neuron Weights in Vocabulary Spa…
Neural machine translation (NMT) heavily relies on word-level modelling to learn semantic representations of input sentences. However, for languages without natural word delimiters (e.g., Chinese) where input sentences have to be tokenized…
We introduce WARP (Weight-space Adaptive Recurrent Prediction), a simple yet powerful model that unifies weight-space learning with linear recurrence to redefine sequence modeling. Unlike conventional recurrent neural networks (RNNs) which…
Rapid integration of large language models (LLMs) into societal applications has intensified concerns about their alignment with universal ethical principles, as their internal value representations remain opaque despite behavioral…
Current end-to-end deep Reinforcement Learning (RL) approaches require jointly learning perception, decision-making and low-level control from very sparse reward signals and high-dimensional inputs, with little capability of incorporating…
This study investigates how weight decay affects the update behavior of individual neurons in deep neural networks through a combination of applied analysis and experimentation. Weight decay can cause the expected magnitude and angular…
We propose a modular framework for multi-relational learning via tensor decomposition. In our learning setting, the training data contains multiple types of relationships among a set of objects, which we represent by a sparse three-mode…
In multi-user semantic communication, language mismatche poses a significant challenge when independently trained agents interact. We present a novel semantic equalization algorithm that enables communication between agents with different…
Pruning is a widely used technique to compress large language models (LLMs) by removing unimportant weights, but it often suffers from significant performance degradation - especially under semi-structured sparsity constraints. Existing…
Large language models (LLMs) experience significant performance degradation when the input exceeds the pretraining context window, primarily due to the out-of-distribution (OOD) behavior of Rotary Position Embedding (RoPE). Recent studies…
Recent advances in Multimodal Large Language Models (MLLMs) have shown remarkable capabilities in understanding both images and 3D data, yet these modalities face inherent limitations in comprehensively representing object geometry and…
In the evolving landscape of neural network models, one prominent challenge stand out: the significant memory overheads associated with training expansive models. Addressing this challenge, this study delves deep into the Rotated Tensor…
Retrieval-Augmented Language Models (RALMs) have demonstrated significant potential in knowledge-intensive tasks; however, they remain vulnerable to performance degradation when presented with irrelevant or noisy retrieved contexts.…
Large Language Models (LLMs) are predominantly deployed as dense transformers, where every parameter in every feed-forward block is activated for every token. While architecturally simple, this is computationally inefficient, since…
Empirical evidence shows that deep vision networks often represent concepts as directions in latent space with concept information written along directional components in the vector representation of the input. However, the mechanism to…
Attributions aim to identify input pixels that are relevant to the decision-making process. A popular approach involves using modified backpropagation (BP) rules to reverse decisions, which improves interpretability compared to the original…
Current deep neural networks (DNNs) can easily overfit to biased training data with corrupted labels or class imbalance. Sample re-weighting strategy is commonly used to alleviate this issue by designing a weighting function mapping from…
Final-answer-based metrics are commonly used for evaluating large language models (LLMs) on math word problems, often taken as proxies for reasoning ability. However, such metrics conflate two distinct sub-skills: abstract formulation…
The alignment of vision-language representations endows current Vision-Language Models (VLMs) with strong multi-modal reasoning capabilities. However, the interpretability of the alignment component remains uninvestigated due to the…
Rotary Positional Encoding (RoPE) is widely used in modern large language models. However, when sequences are extended beyond the range seen during training, rotary phases can enter out-of-distribution regimes, leading to spurious…
Large Language Models' (LLMs) weight matrices can often be expressed in low-rank form with potential to relax memory and compute resource requirements. Unlike prior efforts that focus on developing novel matrix decompositions, in this work…