Search Results for author:
Found 27 papers, 10 papers with code
VisRL: Intention-Driven Visual Perception via Reinforced Reasoning
Visual understanding is inherently intention-driven - humans selectively focus on different regions of a scene based on their goals.
On Memory Construction and Retrieval for Personalized Conversational Agents
To deliver coherent and personalized experiences in long-term conversations, existing approaches typically perform retrieval augmented response generation by constructing memory banks from conversation history at either the turn-level, session-level, or through summarization techniques. In this paper, we present two key findings: (1) The granularity of memory unit matters: turn-level, session-level, and summarization-based methods each exhibit limitations in both memory retrieval accuracy and the semantic quality of the retrieved content.
Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key
Hallucination remains a major challenge for Large Vision-Language Models (LVLMs).
SCBench: A KV Cache-Centric Analysis of Long-Context Methods
To address these challenges, optimizations for long-context inference have been developed, centered around the KV cache.
LLM2CLIP: Powerful Language Model Unlocks Richer Visual Representation
CLIP is a foundational multimodal model that aligns image and text features into a shared space using contrastive learning on large-scale image-text pairs.
MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention
With the pattern and sparse indices, we perform efficient sparse attention calculations via our optimized GPU kernels to significantly reduce the latency in the pre-filling stage of long-context LLMs.
Mitigate Position Bias in Large Language Models via Scaling a Single Dimension
This paper first explores the micro-level manifestations of position bias, concluding that attention weights are a micro-level expression of position bias.
A Large-scale Medical Visual Task Adaptation Benchmark
Visual task adaptation has been demonstrated to be effective in adapting pre-trained Vision Transformers (ViTs) to general downstream visual tasks using specialized learnable layers or tokens.
Designing Network Algorithms via Large Language Models
We introduce NADA, the first framework to autonomously design network algorithms by leveraging the generative capabilities of large language models (LLMs).
LLM-RadJudge: Achieving Radiologist-Level Evaluation for X-Ray Report Generation
This study proposes a novel evaluation framework using large language models (LLMs) to compare radiology reports for assessment.
LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression
Additionally, our model is 3x-6x faster than existing prompt compression methods, while accelerating the end-to-end latency by 1. 6x-2. 9x with compression ratios of 2x-5x.
LSPT: Long-term Spatial Prompt Tuning for Visual Representation Learning
Visual Prompt Tuning (VPT) techniques have gained prominence for their capacity to adapt pre-trained Vision Transformers (ViTs) to downstream visual tasks using specialized learnable tokens termed as prompts.
Toward Open-ended Embodied Tasks Solving
Empowering embodied agents, such as robots, with Artificial Intelligence (AI) has become increasingly important in recent years.
AdaMedGraph: Adaboosting Graph Neural Networks for Personalized Medicine
However, selecting the appropriate edge feature to define patient similarity and construct the graph is challenging, given that each patient is depicted by high-dimensional features from diverse sources.
Unified Medical Image Pre-training in Language-Guided Common Semantic Space
To overcome the aforementioned challenges, we propose an Unified Medical Image Pre-training framework, namely UniMedI, which utilizes diagnostic reports as common semantic space to create unified representations for diverse modalities of medical images (especially for 2D and 3D images).
LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression
In long context scenarios, large language models (LLMs) face three main challenges: higher computational cost, performance reduction, and position bias.
Protecting the Future: Neonatal Seizure Detection with Spatial-Temporal Modeling
A timely detection of seizures for newborn infants with electroencephalogram (EEG) has been a common yet life-saving practice in the Neonatal Intensive Care Unit (NICU).
Is Risk-Sensitive Reinforcement Learning Properly Resolved?
Due to the nature of risk management in learning applicable policies, risk-sensitive reinforcement learning (RSRL) has been realized as an important direction.
Adaptive Policy Learning for Offline-to-Online Reinforcement Learning
In this paper, we consider an offline-to-online setting where the agent is first learned from the offline dataset and then trained online, and propose a framework called Adaptive Policy Learning for effectively taking advantage of offline and online data.
Bootstrapped Transformer for Offline Reinforcement Learning
Offline reinforcement learning (RL) aims at learning policies from previously collected static trajectory data without interacting with the real environment.
Towards Applicable Reinforcement Learning: Improving the Generalization and Sample Efficiency with Policy Ensemble
Considering the great performance of ensemble methods on both accuracy and generalization in supervised learning (SL), we design a robust and applicable method named Ensemble Proximal Policy Optimization (EPPO), which learns ensemble policies in an end-to-end manner.
VRL3: A Data-Driven Framework for Visual Deep Reinforcement Learning
We propose VRL3, a powerful data-driven framework with a simple design for solving challenging visual deep reinforcement learning (DRL) tasks.
Variational oracle guiding for reinforcement learning
How to make intelligent decisions is a central problem in machine learning and cognitive science.
Deep Ensemble Policy Learning
Ensemble learning, which can consistently improve the prediction performance in supervised learning, has drawn increasing attentions in reinforcement learning (RL).
Adaptive Q-learning for Interaction-Limited Reinforcement Learning
Specifically, we explicitly consider the difference between the online and offline data and apply an adaptive update scheme accordingly, i. e., a pessimistic update strategy for the offline dataset and a greedy or no pessimistic update scheme for the online dataset.
P-BN: Towards Effective Batch Normalization in the Path Space
Hence, some new algorithms that conduct optimizations directly in the path space (the path space is proven to be PSI) were developed, such as Stochastic Gradient Descent (SGD) in the path space, and it was shown that SGD in the path space is superior to that in the weight space.
Expressiveness in Deep Reinforcement Learning
Based on our observations, we formally define expressiveness of the state extractor as the rank of the matrix composed by representations.
