Search Results for author:
Found 41 papers, 14 papers with code
R.I.P.: Better Models by Survival of the Fittest Prompts
Using Llama 3. 1-8B-Instruct, RIP improves AlpacaEval2 LC Win Rate by 9. 4%, Arena-Hard by 8. 7%, and WildBench by 9. 9%.
Step-KTO: Optimizing Mathematical Reasoning through Stepwise Binary Feedback
Large language models (LLMs) have recently demonstrated remarkable success in mathematical reasoning.
Computing Approximate Graph Edit Distance via Optimal Transport
We argue that while pairwise vertex features can capture the coupling cost (discrepancy) of a pair of vertices, the vertex coupling matrix should be derived from the vertex-pair cost matrix through a more well-established method that is aware of the global context of the graph pair, such as optimal transport.
From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge
Assessment and evaluation have long been critical challenges in artificial intelligence (AI) and natural language processing (NLP).
DySpec: Faster Speculative Decoding with Dynamic Token Tree Structure
Under low temperature setting, DySpec can improve the throughput up to 9. 1$\times$ and reduce the latency up to 9. 4$\times$ on Llama2-70B.
Thinking LLMs: General Instruction Following with Thought Generation
LLMs are typically trained to answer user questions or follow instructions similarly to how human experts respond.
EmbedLLM: Learning Compact Representations of Large Language Models
Many existing methods repeatedly learn task-specific representations of Large Language Models (LLMs), which leads to inefficiencies in both time and computational resources.
Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge
Large Language Models (LLMs) are rapidly surpassing human knowledge in many domains.
Expressive Gaussian Human Avatars from Monocular RGB Video
Nuanced expressiveness, particularly through fine-grained hand and facial expressions, is pivotal for enhancing the realism and vitality of digital human representations.
RouteLLM: Learning to Route LLMs with Preference Data
Large language models (LLMs) exhibit impressive capabilities across a wide range of tasks, yet the choice of which model to use often involves a trade-off between performance and cost.
From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline
The rapid evolution of Large Language Models (LLMs) has outpaced the development of model evaluation, highlighting the need for continuous curation of new, challenging benchmarks.
Gaussian Head & Shoulders: High Fidelity Neural Upper Body Avatars with Anchor Gaussian Guided Texture Warping
By equipping the most recent 3D Gaussian Splatting representation with head 3D morphable models (3DMM), existing methods manage to create head avatars with high fidelity.
LTOS: Layout-controllable Text-Object Synthesis via Adaptive Cross-attention Fusions
Controllable text-to-image generation synthesizes visual text and objects in images with certain conditions, which are frequently applied to emoji and poster generation.
Blockchain-based Pseudonym Management for Vehicle Twin Migrations in Vehicular Edge Metaverse
As highly computerized avatars of Vehicular Metaverse Users (VMUs), the Vehicle Twins (VTs) deployed in edge servers can provide valuable metaverse services to improve driving safety and on-board satisfaction for their VMUs throughout journeys.
ClusteringSDF: Self-Organized Neural Implicit Surfaces for 3D Decomposition
3D decomposition/segmentation still remains a challenge as large-scale 3D annotated data is not readily available.
Enhancing the Performance of DeepReach on High-Dimensional Systems through Optimizing Activation Functions
Hamilton-Jacobi Reachability Analysis is a formal verification method that guarantees performance and safety for dynamical systems and is widely applicable to various tasks and challenges.
Education distillation:getting student models to learn in shcools
Specifically, it is proposed to take fragmented student models divided from the complete student model as lower-grade models.
Pairwise Proximal Policy Optimization: Harnessing Relative Feedback for LLM Alignment
In summary, this work introduces a simpler yet effective approach for aligning LLMs to human preferences through relative feedback.
GraspGF: Learning Score-based Grasping Primitive for Human-assisting Dexterous Grasping
In this paper, we propose a novel task called human-assisting dexterous grasping that aims to train a policy for controlling a robotic hand's fingers to assist users in grasping objects.
ARF-Plus: Controlling Perceptual Factors in Artistic Radiance Fields for 3D Scene Stylization
We highlight a research gap in radiance fields style transfer, the lack of sufficient perceptual controllability, motivated by the existing concept in the 2D image style transfer.
Blockchain-empowered Federated Learning for Healthcare Metaverses: User-centric Incentive Mechanism with Optimal Data Freshness
Given the revolutionary role of metaverses, healthcare metaverses are emerging as a transformative force, creating intelligent healthcare systems that offer immersive and personalized services.
PanoDiffusion: 360-degree Panorama Outpainting via Diffusion
Generating complete 360-degree panoramas from narrow field of view images is ongoing research as omnidirectional RGB data is not readily available.
Perceptual Quality Assessment of NeRF and Neural View Synthesis Methods for Front-Facing Views
We measured the quality of videos synthesized by several NVS methods in a well-controlled perceptual quality assessment experiment as well as with many existing state-of-the-art image/video quality metrics.
$α$Surf: Implicit Surface Reconstruction for Semi-Transparent and Thin Objects with Decoupled Geometry and Opacity
While neural radiance field (NeRF) based methods can model semi-transparency and achieve photo-realistic quality in synthesized novel views, their volumetric geometry representation tightly couples geometry and opacity, and therefore cannot be easily converted into surfaces without introducing artifacts.
A Reduction-based Framework for Sequential Decision Making with Delayed Feedback
We study stochastic delayed feedback in general multi-agent sequential decision making, which includes bandits, single-agent Markov decision processes (MDPs), and Markov games (MGs).
MTU-Net: Multi-level TransUNet for Space-based Infrared Tiny Ship Detection
Due to the extremely large image coverage area (e. g., thousands square kilometers), candidate targets in these images are much smaller, dimer, more changeable than those targets observed by aerial-based and land-based imaging devices.
Domain Randomization-Enhanced Depth Simulation and Restoration for Perceiving and Grasping Specular and Transparent Objects
Commercial depth sensors usually generate noisy and missing depths, especially on specular and transparent objects, which poses critical issues to downstream depth or point cloud-based tasks.
Towards Human-Level Bimanual Dexterous Manipulation with Reinforcement Learning
In this study, we propose the Bimanual Dexterous Hands Benchmark (Bi-DexHands), a simulator that involves two dexterous hands with tens of bimanual manipulation tasks and thousands of target objects.
D$^2$NeRF: Self-Supervised Decoupling of Dynamic and Static Objects from a Monocular Video
We introduce Decoupled Dynamic Neural Radiance Field (D$^2$NeRF), a self-supervised approach that takes a monocular video and learns a 3D scene representation which decouples moving objects, including their shadows, from the static background.
GraspARL: Dynamic Grasping via Adversarial Reinforcement Learning
we formulate the dynamic grasping problem as a 'move-and-grasp' game, where the robot is to pick up the object on the mover and the adversarial mover is to find a path to escape it.
$ \text{T}^3 $OMVP: A Transformer-based Time and Team Reinforcement Learning Scheme for Observation-constrained Multi-Vehicle Pursuit in Urban Area
Although there are some achievements in the field of MVP in the open space environment, the urban area brings complicated road structures and restricted moving spaces as challenges to the resolution of MVP games.
Nearly Optimal Policy Optimization with Stable at Any Time Guarantee
Policy optimization methods are one of the most widely used classes of Reinforcement Learning (RL) algorithms.
RoboAssembly: Learning Generalizable Furniture Assembly Policy in a Novel Multi-robot Contact-rich Simulation Environment
Part assembly is a typical but challenging task in robotics, where robots assemble a set of individual parts into a complete shape.
A Credibility-aware Swarm-Federated Deep Learning Framework in Internet of Vehicles
This paper proposes a Swarm-Federated Deep Learning framework in the IoV system (IoV-SFDL) that integrates SL into the FDL framework.
VAT-Mart: Learning Visual Action Trajectory Proposals for Manipulating 3D ARTiculated Objects
In this paper, we propose object-centric actionable visual priors as a novel perception-interaction handshaking point that the perception system outputs more actionable guidance than kinematic structure estimation, by predicting dense geometry-aware, interaction-aware, and task-aware visual action affordance and trajectory proposals.
A Reduction-Based Framework for Conservative Bandits and Reinforcement Learning
We also obtain a new upper bound for conservative low-rank MDP.
A Multi-intersection Vehicular Cooperative Control based on End-Edge-Cloud Computing
In particular, we propose a Multi-intersection Vehicular Cooperative Control (MiVeCC) to enable cooperation among vehicles in a large area with multiple unsignalized intersections.
Sanity-Checking Pruning Methods: Random Tickets can Win the Jackpot
In this paper, we conduct sanity checks for the above beliefs on several recent unstructured pruning methods and surprisingly find that: (1) A set of methods which aims to find good subnetworks of the randomly-initialized network (which we call "initial tickets"), hardly exploits any information from the training data; (2) For the pruned networks obtained by these methods, randomly changing the preserved weights in each layer, while keeping the total number of preserved weights unchanged per layer, does not affect the final performance.
Light Field Image Super-Resolution Using Deformable Convolution
In this paper, we propose a deformable convolution network (i. e., LF-DFnet) to handle the disparity problem for LF image SR.
DeOccNet: Learning to See Through Foreground Occlusions in Light Fields
In this paper, we handle the LF de-occlusion (LF-DeOcc) problem using a deep encoder-decoder network (namely, DeOccNet).
