Search Results for author:
Found 37 papers, 17 papers with code
MCTS-Judge: Test-Time Scaling in LLM-as-a-Judge for Code Correctness Evaluation
The LLM-as-a-Judge paradigm shows promise for evaluating generative content but lacks reliability in reasoning-intensive scenarios, such as programming.
Make-A-Character 2: Animatable 3D Character Generation From a Single Image
This report introduces Make-A-Character 2, an advanced system for generating high-quality 3D characters from single portrait photographs, ideal for game development and digital human applications.
UAVs Meet LLMs: Overviews and Perspectives Toward Agentic Low-Altitude Mobility
Low-altitude mobility, exemplified by unmanned aerial vehicles (UAVs), has introduced transformative advancements across various domains, like transportation, logistics, and agriculture.
Efficient Video Face Enhancement with Enhanced Spatial-Temporal Consistency
In Stage \Rmnum{1}, we learn the model with a regularizer mitigating the codebook collapse problem.
The Implicit Bias of Gradient Descent on Separable Multiclass Data
Implicit bias describes the phenomenon where optimization-based training algorithms, without explicit regularization, show a preference for simple estimators even when more complex estimators have equal objective values.
Deploying Ten Thousand Robots: Scalable Imitation Learning for Lifelong Multi-Agent Path Finding
Lifelong Multi-Agent Path Finding (LMAPF) is a variant of MAPF where agents are continually assigned new goals, necessitating frequent re-planning to accommodate these dynamic changes.
WorldCuisines: A Massive-Scale Benchmark for Multilingual and Multicultural Visual Question Answering on Global Cuisines
This benchmark includes a visual question answering (VQA) dataset with text-image pairs across 30 languages and dialects, spanning 9 language families and featuring over 1 million data points, making it the largest multicultural VQA benchmark to date.
DelTA: An Online Document-Level Translation Agent Based on Multi-Level Memory
Large language models (LLMs) have achieved reasonable quality improvements in machine translation (MT).
Herald: A Natural Language Annotated Lean 4 Dataset
A significant challenge in training LLMs for these formal languages is the lack of parallel datasets that align natural language with formal language proofs.
ET-Plan-Bench: Embodied Task-level Planning Benchmark Towards Spatial-Temporal Cognition with Foundation Models
To further explore this area, we introduce a new embodied task planning benchmark, ET-Plan-Bench, which specifically targets embodied task planning using LLMs.
MambaOcc: Visual State Space Model for BEV-based Occupancy Prediction with Local Adaptive Reordering
Occupancy prediction has attracted intensive attention and shown great superiority in the development of autonomous driving systems.
GOReloc: Graph-based Object-Level Relocalization for Visual SLAM
It determines the pose of a camera sensor by robustly associating the object detections in the current frame with 3D objects in a lightweight object-level map.
TasTe: Teaching Large Language Models to Translate through Self-Reflection
The evaluation results in four language directions on the WMT22 benchmark reveal the effectiveness of our approach compared to existing methods.
AMCEN: An Attention Masking-based Contrastive Event Network for Two-stage Temporal Knowledge Graph Reasoning
To achieve more accurate TKG reasoning, we propose an attention masking-based contrastive event network (AMCEN) with local-global temporal patterns for the two-stage prediction of future events.
Sim2Real in Reconstructive Spectroscopy: Deep Learning with Augmented Device-Informed Data Simulation
This work proposes a deep learning (DL)-based framework, namely Sim2Real, for spectral signal reconstruction in reconstructive spectroscopy, focusing on efficient data sampling and fast inference time.
Near-Interpolators: Rapid Norm Growth and the Trade-Off between Interpolation and Generalization
Under a random matrix theoretic assumption on the data distribution and an eigendecay assumption on the data covariance matrix $\boldsymbol{\Sigma}$, we demonstrate that any near-interpolator exhibits rapid norm growth: for $\tau$ fixed, $\boldsymbol{\beta}$ has squared $\ell_2$-norm $\mathbb{E}[\|{\boldsymbol{\beta}}\|_{2}^{2}] = \Omega(n^{\alpha})$ where $n$ is the number of samples and $\alpha >1$ is the exponent of the eigendecay, i. e., $\lambda_i(\boldsymbol{\Sigma}) \sim i^{-\alpha}$.
VOOM: Robust Visual Object Odometry and Mapping using Hierarchical Landmarks
Meanwhile, local bundle adjustment is performed utilizing the objects and points-based covisibility graphs in our visual object mapping process.
Make-A-Character: High Quality Text-to-3D Character Generation within Minutes
There is a growing demand for customized and expressive 3D characters with the emergence of AI agents and Metaverse, but creating 3D characters using traditional computer graphics tools is a complex and time-consuming task.
Unified Binary and Multiclass Margin-Based Classification
The notion of margin loss has been central to the development and analysis of algorithms for binary classification.
Neural Collapse in Multi-label Learning with Pick-all-label Loss
We study deep neural networks for the multi-label classification (MLab) task through the lens of neural collapse (NC).
Diversity from Human Feedback
DivHF learns a behavior descriptor consistent with human preference by querying human feedback.
Benign Overfitting and Grokking in ReLU Networks for XOR Cluster Data
Second, they can undergo a period of classical, harmful overfitting -- achieving a perfect fit to training data with near-random performance on test data -- before transitioning ("grokking") to near-optimal generalization later in training.
UniG-Encoder: A Universal Feature Encoder for Graph and Hypergraph Node Classification
In this work, a universal feature encoder for both graph and hypergraph representation learning is designed, called UniG-Encoder.
Ranked #7 on
Node Classification
on Cornell
On Classification-Calibration of Gamma-Phi Losses
Gamma-Phi losses constitute a family of multiclass classification loss functions that generalize the logistic and other common losses, and have found application in the boosting literature.
Heterogeneous Multi-agent Zero-Shot Coordination by Coevolution
Generating agents that can achieve zero-shot coordination (ZSC) with unseen partners is a new challenge in cooperative multi-agent reinforcement learning (MARL).
MORE: A Metric Learning Based Framework for Open-domain Relation Extraction
To address these problems, in this work, we propose a novel learning framework named MORE (Metric learning-based Open Relation Extraction).
Consistent Interpolating Ensembles via the Manifold-Hilbert Kernel
Recent research in the theory of overparametrized learning has sought to establish generalization guarantees in the interpolating regime.
Distributed Reinforcement Learning for Robot Teams: A Review
This review aims to provide an analysis of the state-of-the-art in distributed MARL for multi-robot cooperation.
Multi-agent Reinforcement Learning
reinforcement-learning
+2
Learning from Label Proportions by Learning with Label Noise
Learning from label proportions (LLP) is a weakly supervised classification problem where data points are grouped into bags, and the label proportions within each bag are observed instead of the instance-level labels.
FCMNet: Full Communication Memory Net for Team-Level Cooperation in Multi-Agent Systems
There, our comparison results show that FCMNet outperforms state-of-the-art communication-based reinforcement learning methods in all StarCraft II micromanagement tasks, and value decomposition methods in certain tasks.
VC dimension of partially quantized neural networks in the overparametrized regime
Indeed, existing applications of VC theory to large networks obtain upper bounds on VC dimension that are proportional to the number of weights, and for a large class of networks, these upper bound are known to be tight.
Evolutionary Diversity Optimization with Clustering-based Selection for Reinforcement Learning
However, due to the inefficient selection mechanisms, these methods cannot fully guarantee both high quality and diversity.
Real-Time Video Super-Resolution on Smartphones with Deep Learning, Mobile AI 2021 Challenge: Report
Video super-resolution has recently become one of the most important mobile-related problems due to the rise of video communication and streaming services.
An Exact Solver for the Weston-Watkins SVM Subproblem
Recent empirical evidence suggests that the Weston-Watkins support vector machine is among the best performing multiclass extensions of the binary SVM.
Are Top School Students More Critical of Their Professors? Mining Comments on RateMyProfessor.com
Next, we perform exploratory data analysis to delve into the data.
Weston-Watkins Hinge Loss and Ordered Partitions
A recent empirical comparison of nine such formulations [Do\v{g}an et al. 2016] recommends the variant proposed by Weston and Watkins (WW), despite the fact that the WW-hinge loss is not calibrated with respect to the 0-1 loss.
Weak Supervision Enhanced Generative Network for Question Generation
More specifically, we devise a discriminator, Relation Guider, to capture the relations between the whole passage and the associated answer and then the Multi-Interaction mechanism is deployed to transfer the knowledge dynamically for our question generation system.
