Related papers: Thermodynamic Focusing for Inference-Time Search: …
Despite the recent success of Large Language Models (LLMs), it remains challenging to feed LLMs with long prompts due to the fixed size of LLM inputs. As a remedy, prompt compression becomes a promising solution by removing redundant tokens…
We introduce a novel speaker model \textsc{Kefa} for navigation instruction generation. The existing speaker models in Vision-and-Language Navigation suffer from the large domain gap of vision features between different environments and…
Large language models have exhibited intriguing in-context learning capability, achieving promising zero- and few-shot performance without updating the parameters. However, conventional in-context learning is usually restricted by length…
The strong capabilities of recent Large Language Models (LLMs) have made them highly effective for zero-shot re-ranking task. Attention-based re-ranking methods, which derive relevance scores directly from attention weights, offer an…
Optimizing objective functions subject to constraints is fundamental in many real-world applications. However, these constraints are often not readily defined and must be inferred from expert agent behaviors, a problem known as Inverse…
We propose a new perspective for the evaluation of matching procedures by considering the complexity of the function class they belong to. Under this perspective we provide theoretical guarantees on post-matching covariate balance through a…
Language models, especially pre-trained large language models, have showcased remarkable abilities as few-shot in-context learners (ICL), adept at adapting to new tasks with just a few demonstrations in the input context. However, the…
In-context learning has become a popular paradigm in natural language processing. However, its performance can be significantly influenced by the order of in-context demonstration examples. In this paper, we found that causal language…
We present a method that achieves state-of-the-art results on challenging (few-shot) layout-to-image generation tasks by accurately modeling textures, structures and relationships contained in a complex scene. After compressing RGB images…
Language model alignment is a critical step in training modern generative language models. Alignment targets to improve win rate of a sample from the aligned model against the base model. Today, we are increasingly using inference-time…
In-context learning \ -- performing tasks based on examples given in the prompt \ -- is an important capability that has emerged in large language models and has received significant attention in both theory and practice. Existing…
Sentence compression reduces the length of text by removing non-essential content while preserving important facts and grammaticality. Unsupervised objective driven methods for sentence compression can be used to create customized models…
We study inverse reinforcement learning (IRL) and imitation learning (IM), the problems of recovering a reward or policy function from expert's demonstrated trajectories. We propose a new way to improve the learning process by adding a…
Combinatorial optimization is frequently used in computer vision. For instance, in applications like semantic segmentation, human pose estimation and action recognition, programs are formulated for solving inference in Conditional Random…
Feature transformation aims to generate new pattern-discriminative feature space from original features to improve downstream machine learning (ML) task performances. However, the discrete search space for the optimal feature explosively…
While large language models (LLMs) exhibit strong reasoning abilities, their performance on complex tasks is often constrained by the limitations of their internal knowledge. A compelling approach to overcome this challenge is to augment…
In this paper, we present a random-forest based fast cascaded regression model for face alignment, via a novel local feature. Our proposed local lightweight feature, namely intimacy definition feature (IDF), is more discriminative than…
This paper proposes TIP-Search, a time-predictable inference scheduling framework for real-time market prediction under uncertain workloads. Motivated by the strict latency demands in high-frequency financial systems, TIP-Search dynamically…
We propose a novel reinforcement learning framework for post training large language models that does not rely on human in the loop feedback. Instead, our approach uses cross attention signals within the model itself to derive a self…
Pre-trained language models have shown excellent results in few-shot learning scenarios using in-context learning. Although it is impressive, the size of language models can be prohibitive to make them usable in on-device applications, such…