Related papers: IGD: Token Decisiveness Modeling via Information G…

Generative recommendation (GR) is an emerging paradigm that tokenizes items into discrete tokens and learns to autoregressively generate the next tokens as predictions. While this token-generation paradigm is expected to surpass traditional…

Large language models (LLMs) now exhibit strong multi-step reasoning abilities, but existing inference-time scaling methods remain computationally expensive, often relying on extensive sampling or external evaluators. We propose a…

The prevailing assumption of an exponential decay in large language model (LLM) reliability with sequence length, predicated on independent per-token error probabilities, posits an inherent limitation for long autoregressive outputs. Our…

Large Language Models(LLMs) have been attracting attention due to a ability called in-context learning(ICL). ICL, without updating the parameters of a LLM, it is possible to achieve highly accurate inference based on rules ``in the…

Knowledge Graphs (KGs) represent relationships between entities in a graph structure and have been widely studied as promising tools for realizing recommendations that consider the accurate content information of items. However, traditional…

Likelihood-based deep generative models (DGMs) have gained significant attention for their ability to approximate the distributions of high-dimensional data. However, these models lack a performance guarantee in assigning higher likelihood…

Model compression is critical for deploying deep learning models on resource-constrained devices. We introduce a novel method enhancing knowledge distillation with integrated gradients (IG) as a data augmentation strategy. Our approach…

The great success of Large Language Models (LLMs) has expanded the potential of multimodality, contributing to the gradual evolution of General Artificial Intelligence (AGI). A true AGI agent should not only possess the capability to…

The reasoning and generalization capabilities of LLMs can help us better understand user preferences and item characteristics, offering exciting prospects to enhance recommendation systems. Though effective while user-item interactions are…

One of the most striking findings in modern research on large language models (LLMs) is that scaling up compute during training leads to better results. However, less attention has been given to the benefits of scaling compute during…

Large Language Models (LLMs) achieve strong performance through extended inference-time deliberation, yet how their reasoning failures arise remains poorly understood. By analyzing model-generated reasoning trajectories, we find that errors…

Speculative decoding accelerates large language model (LLM) inference by using a small draft model to generate candidate tokens for a larger target model to verify. The efficacy of this technique hinges on the trade-off between the time…

Algorithmic trading requires short-term tactical decisions consistent with long-term financial objectives. Reinforcement Learning (RL) has been applied to such problems, but adoption is limited by myopic behaviour and opaque policies. Large…

Given the widespread adoption and usage of Large Language Models (LLMs), it is crucial to have flexible and interpretable evaluations of their instruction-following ability. Preference judgments between model outputs have become the de…

In learning to defer, a predictor identifies risky decisions and defers them to a human expert. One key issue with this setup is that the expert may end up over-relying on the machine's decisions, due to anchoring bias. At the same time,…

Large language models (LLMs) are increasingly applied to sequential decision-making through in-context learning (ICL), yet their effectiveness is highly sensitive to prompt quality. Effective prompts should meet three principles: focus on…

This research aims to unravel how large language models (LLMs) iteratively refine token predictions through internal processing. We utilized a logit lens technique to analyze the model's token predictions derived from intermediate…

Abstract Modern image generation (IG) models have been shown to capture rich semantics valuable for image understanding (IU) tasks. However, the potential of IU models to improve IG performance remains uncharted. We address this issue using…

The emergence of discourse-like tokens such as "wait" and "therefore" in large language models (LLMs) has offered a unique window into their reasoning processes. However, systematic analyses of how such signals vary across training…

Large Language Models (LLMs) show promise as data analysis agents, but existing benchmarks overlook the iterative nature of the field, where experts' decisions evolve with deeper insights of the dataset. To address this, we introduce…