Search Results for author:
Found 29 papers, 18 papers with code
S$^2$R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning
In this work, we introduce S$^2$R, an efficient framework that enhances LLM reasoning by teaching models to self-verify and self-correct during inference.
CRoF: CLIP-based Robust Few-shot Learning on Noisy Labels
Noisy labels threaten the robustness of few-shot learning (FSL) due to the inexact features in a new domain.
Imitate Before Detect: Aligning Machine Stylistic Preference for Machine-Revised Text Detection
Large Language Models (LLMs) have revolutionized text generation, making detecting machine-generated text increasingly challenging.
SpikMamba: When SNN meets Mamba in Event-based Human Action Recognition
To address these issues, we propose the SpikMamba framework, which combines the energy efficiency of spiking neural networks and the long sequence modeling capability of Mamba to efficiently capture global features from spatially sparse and high a temporal resolution event data.
AFlow: Automating Agentic Workflow Generation
Large language models (LLMs) have demonstrated remarkable potential in solving complex tasks across diverse domains, typically by employing agentic workflows that follow detailed instructions and operational sequences.
Ranked #12 on
Code Generation
on MBPP
Affordances-Oriented Planning using Foundation Models for Continuous Vision-Language Navigation
LLM-based agents have demonstrated impressive zero-shot performance in vision-language navigation (VLN) task.
NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wild
Neural Radiance Fields (NeRFs) have shown remarkable success in synthesizing photorealistic views from multi-view images of static scenes, but face challenges in dynamic, real-world environments with distractors like moving objects, shadows, and lighting changes.
"Where am I?" Scene Retrieval with Language
We define this task as "language-based scene-retrieval" and it is closely related to "coarse-localization," but we are instead searching for a match from a collection of disjoint scenes and not necessarily a large-scale continuous map.
NavCoT: Boosting LLM-Based Vision-and-Language Navigation via Learning Disentangled Reasoning
Vision-and-Language Navigation (VLN), as a crucial research problem of Embodied AI, requires an embodied agent to navigate through complex 3D environments following natural language instructions.
Data Interpreter: An LLM Agent For Data Science
On InfiAgent-DABench, it achieves a 25% performance boost, raising accuracy from 75. 9% to 94. 9%.
S-Agents: Self-organizing Agents in Open-ended Environments
Leveraging large language models (LLMs), autonomous agents have significantly improved, gaining the ability to handle a variety of tasks.
MapGPT: Map-Guided Prompting with Adaptive Path Planning for Vision-and-Language Navigation
Embodied agents equipped with GPT as their brains have exhibited extraordinary decision-making and generalization abilities across various tasks.
A Data-Driven Integrated Framework for Fast-Charging Facility Planning using Multi-Period Bi-Objective Optimization
The case study on the Amsterdam highway network shows how existing traffic data can be used to generate more realistic charging demand scenarios and how it can be integrated and evaluated within the optimization framework for facility planning.
MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework
Remarkable progress has been made on automated problem solving through societies of agents based on large language models (LLMs).
Ranked #21 on
Code Generation
on HumanEval
Generative Semantic Segmentation
To that end, the segmentation mask is expressed with a special type of image (dubbed as maskige).
UniGeo: Unifying Geometry Logical Reasoning via Reformulating Mathematical Expression
Naturally, we also present a unified multi-task Geometric Transformer framework, Geoformer, to tackle calculation and proving problems simultaneously in the form of sequence generation, which finally shows the reasoning ability can be improved on both two tasks by unifying formulation.
Ranked #5 on
Mathematical Reasoning
on PGPS9K
DeepInteraction: 3D Object Detection via Modality Interaction
Existing top-performance 3D object detectors typically rely on the multi-modal fusion strategy.
Unbiased Math Word Problems Benchmark for Mitigating Solving Bias
However, current solvers exist solving bias which consists of data bias and learning bias due to biased dataset and improper training strategy.
LogicSolver: Towards Interpretable Math Word Problem Solving with Logical Prompt-enhanced Learning
To address this issue and make a step towards interpretable MWP solving, we first construct a high-quality MWP dataset named InterMWP which consists of 11, 495 MWPs and annotates interpretable logical formulas based on algebraic knowledge as the grounded linguistic logic of each solution equation.
UltraPose: Synthesizing Dense Pose with 1 Billion Points by Human-body Decoupling 3D Model
However, the popular DensePose-COCO dataset relies on a sophisticated manual annotation system, leading to severe limitations in acquiring the denser and more accurate annotated pose resources.
IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning
Also, we develop a strong IconQA baseline Patch-TRM that applies a pyramid cross-modal Transformer with input diagram embeddings pre-trained on the icon dataset.
Ranked #1 on
Visual Question Answering (VQA)
on IconQA
GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical Reasoning
Therefore, we propose a Geometric Question Answering dataset GeoQA, containing 4, 998 geometric problems with corresponding annotated programs, which illustrate the solving process of the given problems.
Ranked #6 on
Mathematical Reasoning
on PGPS9K
A Guide to Reducing Carbon Emissions through Data Center Geographical Load Shifting
This paper focuses on how data centers can use their geographic load flexibility to reduce carbon emissions through clever interactions with electricity markets.
Cross-Modal Collaborative Representation Learning and a Large-Scale RGBT Benchmark for Crowd Counting
Extensive experiments conducted on the RGBT-CC benchmark demonstrate the effectiveness of our framework for RGBT crowd counting.
Constructing Canonical Feynman Integrals with Intersection Theory
Canonical Feynman integrals are of great interest in the study of scattering amplitudes at the multi-loop level.
High Energy Physics - Theory High Energy Physics - Phenomenology
Efficient Crowd Counting via Structured Knowledge Transfer
Crowd counting is an application-oriented task and its inference efficiency is crucial for real-world applications.
Robot Calligraphy using Pseudospectral Optimal Control in Conjunction with a Novel Dynamic Brush Model
Chinese calligraphy is a unique art form with great artistic value but difficult to master.
Robot Calligraphy using Pseudospectral Optimal Control in Conjunction with a Simulated Brush Model
Chinese calligraphy is a unique form of art that has great artistic value but is difficult to master.
Robotics
