Search Results for author:
Found 46 papers, 26 papers with code
The Singapore Consensus on Global AI Safety Research Priorities
Rapidly improving AI capabilities and autonomy hold significant promise of transformation, but are also driving vigorous debate on how to ensure that AI is safe, i. e., trustworthy, reliable, and secure.
AANet: Virtual Screening under Structural Uncertainty via Alignment and Aggregation
Virtual screening (VS) is a critical component of modern drug discovery, yet most existing methods--whether physics-based or deep learning-based--are developed around holo protein structures with known ligand-bound pockets.
PICD: Versatile Perceptual Image Compression with Diffusion Rendering
To tackle this challenge, we propose versatile perceptual screen image compression with diffusion rendering (PICD), a codec that works well for both screen and natural images.
PharmAgents: Building a Virtual Pharma with Large Language Model Agents
The discovery of novel small molecule drugs remains a critical scientific challenge with far-reaching implications for treating diseases and advancing human health.
DAPO: An Open-Source LLM Reinforcement Learning System at Scale
Inference scaling empowers LLMs with unprecedented reasoning ability, with reinforcement learning as the core technique to elicit complex reasoning.
Pushing the boundaries of Structure-Based Drug Design through Collaboration with Large Language Models
Structure-Based Drug Design (SBDD) has revolutionized drug discovery by enabling the rational design of molecules for specific protein targets.
CoopDETR: A Unified Cooperative Perception Framework for 3D Detection via Object Query
Cooperative perception enhances the individual perception capabilities of autonomous vehicles (AVs) by providing a comprehensive view of the environment.
Contrastive Private Data Synthesis via Weighted Multi-PLM Fusion
WASP utilizes limited private samples for more accurate private data distribution estimation via a Top-Q voting mechanism, and leverages low-quality synthetic samples for contrastive generation via collaboration among dynamically weighted multiple pre-trained models. Extensive experiments on 6 well-developed datasets with 6 open-source and 3 closed-source PLMs demonstrate the superiority of WASP in improving model performance over diverse downstream tasks.
Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior
Recent advancements in diffusion models have been leveraged to address inverse problems without additional training, and Diffusion Posterior Sampling (DPS) (Chung et al., 2022a) is among the most popular approaches.
IROAM: Improving Roadside Monocular 3D Object Detection Learning from Autonomous Vehicle Data Domain
In-Domain Query Interaction module utilizes a transformer to learn content and depth information for each domain and outputs object queries.
International AI Safety Report
The first International AI Safety Report comprehensively synthesizes the current evidence on the capabilities, risks, and safety of advanced AI systems.
Universal Actions for Enhanced Embodied Foundation Models
Training on diverse, internet-scale data is a key factor in the success of recent large foundation models.
AutoDroid-V2: Boosting SLM-based GUI Agents via Code Generation
Unlike normal coding tasks that can be extensively pre-trained with public datasets, generating UI automation code is challenging due to the diversity, complexity, and variability of target apps.
International Scientific Report on the Safety of Advanced AI (Interim Report)
This is the interim publication of the first International Scientific Report on the Safety of Advanced AI.
Robo-MUTUAL: Robotic Multimodal Task Specification via Unimodal Learning
Multimodal task specification is essential for enhanced robotic performance, where \textit{Cross-modality Alignment} enables the robot to holistically understand complex task instructions.
FuseGen: PLM Fusion for Data-generation based Zero-shot Learning
To mitigate such bias, we propose FuseGen, a novel data generation-based zero-shot learning framework that introduces a new criteria for subset selection from synthetic datasets via utilizing multiple PLMs and trained STMs.
From Theory to Therapy: Reframing SBDD Model Evaluation via Practical Metrics
Recent advancements in structure-based drug design (SBDD) have significantly enhanced the efficiency and precision of drug discovery by generating molecules tailored to bind specific protein pockets.
SIU: A Million-Scale Structural Small Molecule-Protein Interaction Dataset for Unbiased Bioactivity Prediction
Small molecules play a pivotal role in modern medicine, and scrutinizing their interactions with protein targets is essential for the discovery and development of novel, life-saving therapeutics.
Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents
The recent rapid development of large language models (LLMs) has sparked a new wave of technological revolution in medical artificial intelligence (AI).
DecisionNCE: Embodied Multimodal Representations via Implicit Preference Learning
Multimodal pretraining is an effective strategy for the trinity of goals of representation learning in autonomous robots: 1) extracting both local and global task progressions; 2) enforcing temporal consistency of visual representation; 3) capturing trajectory-level language grounding.
Ranked #1 on
Contrastive Learning
on 10,000 People - Human Pose Recognition Data
(using extra training data)
EMIFF: Enhanced Multi-scale Image Feature Fusion for Vehicle-Infrastructure Cooperative 3D Object Detection
In autonomous driving, cooperative perception makes use of multi-view cameras from both vehicles and infrastructure, providing a global vantage point with rich semantic context of road conditions beyond a single vehicle viewpoint.
Consistency Model is an Effective Posterior Sample Approximation for Diffusion Inverse Solvers
Diffusion Inverse Solvers (DIS) are designed to sample from the conditional distribution $p_{\theta}(X_0|y)$, with a predefined diffusion model $p_{\theta}(X_0)$, an operator $f(\cdot)$, and a measurement $y=f(x'_0)$ derived from an unknown image $x'_0$.
Idempotence and Perceptual Image Compression
However, we find that theoretically: 1) Conditional generative model-based perceptual codec satisfies idempotence; 2) Unconditional generative model with idempotence constraint is equivalent to conditional generative codec.
Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security
Next, we discuss several key challenges to achieve intelligent, efficient and secure Personal LLM Agents, followed by a comprehensive survey of representative solutions to address these challenges.
Managing extreme AI risks amid rapid progress
Artificial Intelligence (AI) is progressing rapidly, and companies are shifting their focus to developing generalist AI systems that can autonomously act and pursue goals.
VFLAIR: A Research Library and Benchmark for Vertical Federated Learning
Vertical Federated Learning (VFL) has emerged as a collaborative training paradigm that allows participants with different features of the same group of users to accomplish cooperative training without exposing their raw data or model parameters.
Distributional Soft Actor-Critic with Three Refinements
To address this issue, we previously proposed the Distributional Soft Actor-Critic (DSAC or DSACv1), an off-policy RL algorithm that enhances value estimation accuracy by learning a continuous Gaussian value distribution.
NeRRF: 3D Reconstruction and View Synthesis for Transparent and Specular Objects with Neural Refractive-Reflective Fields
In this paper, we introduce the refractive-reflective field.
Conditional Perceptual Quality Preserving Image Compression
We propose conditional perceptual quality, an extension of the perceptual quality defined in \citet{blau2018perception}, by conditioning it on user defined information.
Query-Policy Misalignment in Preference-Based Reinforcement Learning
To unravel this mystery, we identify a long-neglected issue in the query selection schemes of existing PbRL studies: Query-Policy Misalignment.
PROTO: Iterative Policy Regularized Offline-to-Online Reinforcement Learning
Offline-to-online reinforcement learning (RL), by combining the benefits of offline pretraining and online finetuning, promises enhanced sample efficiency and policy performance.
Feasible Policy Iteration for Safe Reinforcement Learning
A region-wise update rule is developed for the policy improvement step, which maximizes state-value function inside the feasible region and minimizes feasibility function outside it.
DPF: Learning Dense Prediction Fields with Weak Supervision
We showcase the effectiveness of DPFs using two substantially different tasks: high-level semantic parsing and low-level intrinsic image decomposition.
VIMI: Vehicle-Infrastructure Multi-view Intermediate Fusion for Camera-based 3D Object Detection
In autonomous driving, Vehicle-Infrastructure Cooperative 3D Object Detection (VIC3D) makes use of multi-view cameras from both vehicles and traffic infrastructure, providing a global vantage point with rich semantic context of road conditions beyond a single vehicle viewpoint.
AdaptiveNet: Post-deployment Neural Architecture Adaptation for Diverse Edge Environments
Model elastification generates a high-quality search space of model architectures with the guidance of a developer-specified oracle model.
LODE: Locally Conditioned Eikonal Implicit Scene Completion from Sparse LiDAR
In this paper, we propose a novel Eikonal formulation that conditions the implicit representation on localized shape priors which function as dense boundary value constraints, and demonstrate it works on SemanticKITTI and SemanticPOSS.
Mind the Gap: Offline Policy Optimization for Imperfect Rewards
RGM is formulated as a bi-level optimization problem: the upper layer optimizes a reward correction term that performs visitation distribution matching w. r. t.
Mutual Information Regularization for Vertical Federated Learning
However, previous works show that parties without labels (passive parties) in VFL can infer the sensitive label information owned by the party with labels (active party) or execute backdoor attacks to VFL.
Vertical Federated Learning: Concepts, Advances and Challenges
Motivated by the rapid growth in VFL research and real-world applications, we provide a comprehensive review of the concept and algorithms of VFL, as well as current advances and challenges in various aspects, including effectiveness, efficiency, and privacy.
TOIST: Task Oriented Instance Segmentation Transformer with Noun-Pronoun Distillation
As such, we study the challenging problem of task oriented detection, which aims to find objects that best afford an action indicated by verbs like sit comfortably on.
Correcting the Sub-optimal Bit Allocation
In this paper, we investigate the problem of bit allocation in Neural Video Compression (NVC).
Bit Allocation using Optimization
In this paper, we consider the problem of bit allocation in Neural Video Compression (NVC).
When Data Geometry Meets Deep Function: Generalizing Offline Reinforcement Learning
In offline reinforcement learning (RL), one detrimental issue to policy learning is the error accumulation of deep Q function in out-of-distribution (OOD) areas.
Semi-supervised Implicit Scene Completion from Sparse LiDAR
Recent advances show that semi-supervised implicit representation learning can be achieved through physical constraints like Eikonal equations.
Cerberus Transformer: Joint Semantic, Affordance and Attribute Parsing
Multi-task indoor scene understanding is widely considered as an intriguing formulation, as the affinity of different tasks may lead to improved performance.
Ranked #63 on
Semantic Segmentation
on NYU Depth v2
PQ-Transformer: Jointly Parsing 3D Objects and Layouts from Point Clouds
Such a scheme has two limitations: 1) Storing and running several networks for different tasks are expensive for typical robotic platforms.
