Search Results for author:
Found 32 papers, 10 papers with code
PhysUniBench: An Undergraduate-Level Physics Reasoning Benchmark for Multimodal Models
These results highlight that current MLLMs struggle with advanced physics reasoning, especially on multi-step problems and those requiring precise diagram interpretation.
Block-wise Adaptive Caching for Accelerating Diffusion Policy
BAC achieves lossless action generation acceleration by adaptively updating and reusing cached features at the block level, based on a key observation that feature similarities vary non-uniformly across timesteps and locks.
CPRet: A Dataset, Benchmark, and Model for Retrieval in Competitive Programming
Due to the lack of both data and models, solving this problem is challenging.
Point2Primitive: CAD Reconstruction from Point Cloud by Direct Primitive Prediction
Recovering CAD models from point clouds, especially the sketch-extrusion process, can be seen as the process of rebuilding the topology and extrusion primitives.
An Efficient and Mixed Heterogeneous Model for Image Restoration
This hierarchical and adaptive design enables the model to leverage the strengths of CNNs in local feature extraction, Mamba in global context modeling, and attention mechanisms in dynamic feature refinement.
Pretrained Bayesian Non-parametric Knowledge Prior in Robotic Long-Horizon Reinforcement Learning
Reinforcement learning (RL) methods typically learn new tasks from scratch, often disregarding prior knowledge that could accelerate the learning process.
Data-Agnostic Robotic Long-Horizon Manipulation with Vision-Language-Guided Closed-Loop Feedback
Recent advances in language-conditioned robotic manipulation have leveraged imitation and reinforcement learning to enable robots to execute tasks from human commands.
3DAxisPrompt: Promoting the 3D Grounding and Reasoning in GPT-4o
Multimodal Large Language Models (MLLMs) exhibit impressive capabilities across a variety of tasks, especially when equipped with carefully designed visual prompts.
JAQ: Joint Efficient Architecture Design and Low-Bit Quantization with Hardware-Software Co-Exploration
The co-design of neural network architectures, quantization precisions, and hardware accelerators offers a promising approach to achieving an optimal balance between performance and efficiency, particularly for model deployment on resource-constrained edge devices.
ACL: Activating Capability of Linear Attention for Image Restoration
ACL integrates linear attention blocks instead of SSM within Mamba, serving as the core component of encoders/decoders, and aims to preserve a global perspective while boosting computational efficiency.
EMS: Adaptive Evict-then-Merge Strategy for Head-wise KV Cache Compression Based on Global-Local Importance
However, these approaches often produce biased distributions of important tokens due to the influence of accumulated attention scores or positional encoding.
GAQAT: gradient-adaptive quantization-aware training for domain generalization
To address this limitation, we propose a novel Gradient-Adaptive Quantization-Aware Training (GAQAT) framework for DG.
CATP-LLM: Empowering Large Language Models for Cost-Aware Tool Planning
To push this paradigm toward practical applications, it is crucial for LLMs to consider tool execution costs (e. g. execution time) for tool planning.
RTF-Q: Efficient Unsupervised Domain Adaptation with Retraining-free Quantization
To address these limitations, we propose efficient unsupervised domain adaptation with ReTraining-Free Quantization (RTF-Q).
PRANCE: Joint Token-Optimization and Structural Channel-Pruning for Adaptive ViT Inference
We introduce PRANCE, a Vision Transformer compression framework that jointly optimizes the activated channels and reduces tokens, based on the characteristics of inputs.
Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers
Recent advancements in diffusion models, particularly the architectural transformation from UNet-based models to Diffusion Transformers (DiTs), significantly improve the quality and scalability of image and video generation.
Towards Lightweight Graph Neural Network Search with Curriculum Graph Sparsification
To search for optimal lightweight Graph Neural Networks (GNNs), we propose a Lightweight Graph Neural Architecture Search with Graph SparsIfication and Network Pruning (GASSIP) method.
Evaluating the Generalization Ability of Quantized LLMs: Benchmark, Analysis, and Toolbox
Based on this benchmark, we conduct extensive experiments with two well-known LLMs (English and Chinese) and four quantization algorithms to investigate this topic in-depth, yielding several counter-intuitive and valuable findings, e. g., models quantized using a calibration set with the same distribution as the test data are not necessarily optimal.
One QuantLLM for ALL: Fine-tuning Quantized LLMs Once for Efficient Deployments
Large Language Models (LLMs) have advanced rapidly but face significant memory demands.
RealTCD: Temporal Causal Discovery from Interventional Data with Large Language Model
In the field of Artificial Intelligence for Information Technology Operations, causal discovery is pivotal for operation and maintenance of graph construction, facilitating downstream industrial tasks such as root cause analysis.
TMPQ-DM: Joint Timestep Reduction and Quantization Precision Selection for Efficient Diffusion Models
Diffusion models have emerged as preeminent contenders in the realm of generative models.
Investigating the Impact of Quantization on Adversarial Robustness
Quantization is a promising technique for reducing the bit-width of deep models to improve their runtime performance and storage efficiency, and thus becomes a fundamental step for deployment.
Retraining-free Model Quantization via One-Shot Weight-Coupling Learning
Conversely, mixed-precision quantization (MPQ) is advocated to compress the model effectively by allocating heterogeneous bit-width for layers.
Towards Fair and Comprehensive Comparisons for Image-Based 3D Object Detection
In this work, we build a modular-designed codebase, formulate strong training recipes, design an error diagnosis toolbox, and discuss current methods for image-based 3D object detection.
Characterizing Speed Performance of Multi-Agent Reinforcement Learning
Multi-Agent Reinforcement Learning (MARL) has achieved significant success in large-scale AI systems and big-data applications such as smart grids, surveillance, etc.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
RGAT: A Deeper Look into Syntactic Dependency Information for Coreference Resolution
Our experiments on a public Gendered Ambiguous Pronouns (GAP) dataset show that with the supervision learning of the syntactic dependency graph and without fine-tuning the entire BERT, we increased the F1-score of the previous best model (RGCN-with-BERT) from 80. 3% to 82. 5%, compared to the F1-score by single BERT embeddings from 78. 5% to 82. 5%.
DIVA: A Dirichlet Process Mixtures Based Incremental Deep Clustering Algorithm via Variational Auto-Encoder
Generative model-based deep clustering frameworks excel in classifying complex data, but are limited in handling dynamic and complex features because they require prior knowledge of the number of clusters.
DNG: Taxonomy Expansion by Exploring the Intrinsic Directed Structure on Non-gaussian Space
Specifically, the inherited feature originates from "parent" nodes and is weighted by an inheritance factor.
SEAM: Searching Transferable Mixed-Precision Quantization Policy through Large Margin Regularization
This general and dataset-independent property makes us search for the MPQ policy over a rather small-scale proxy dataset and then the policy can be directly used to quantize the model trained on a large-scale dataset.
An Empirical Study of Pseudo-Labeling for Image-based 3D Object Detection
We hope this work can provide insights for the image-based 3D detection community under a semi-supervised setting.
Estimating Granger Causality with Unobserved Confounders via Deep Latent-Variable Recurrent Neural Network
We use a generative model with latent variable to build the relationship between the unobserved confounders and the observed variables(tested variable and the proxy variables).
