Search Results for author:
Found 18 papers, 3 papers with code
A Simple Linear Patch Revives Layer-Pruned Large Language Models
With only 5K samples, the retained performance of LinearPatch can be further boosted to 95. 16% within 30 minutes on a single computing card.
Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs
While structured pruning offers a promising avenue for model compression, existing methods often struggle with the detrimental effects of aggressive, simultaneous width and depth reductions, leading to substantial performance degradation.
Chain-of-Focus: Adaptive Visual Search and Zooming for Multimodal Reasoning via RL
Vision language models (VLMs) have achieved impressive performance across a variety of computer vision tasks.
Iterative Tool Usage Exploration for Multimodal Agents via Step-wise Preference Tuning
The data is subsequently used to update the controller for tool usage through preference tuning, producing a SPORT agent.
TongUI: Building Generalized GUI Agents by Learning from Multimodal Web Tutorials
Building Graphical User Interface (GUI) agents is a promising research direction, which simulates human interaction with computers or mobile phones to perform diverse GUI tasks.
Megrez-Omni Technical Report
In this work, we present the Megrez models, comprising a language model (Megrez-3B-Instruct) and a multimodal model (Megrez-3B-Omni).
Explanatory Instructions: Towards Unified Vision Tasks Understanding and Zero-shot Generalization
In this paper, we explore the idea that CV adopts discrete and terminological task definitions (\eg, ``image segmentation''), which may be a key barrier to zero-shot task generalization.
Multi-modal Agent Tuning: Building a VLM-Driven Agent for Efficient Tool Usage
The advancement of large language models (LLMs) prompts the development of multi-modal agents, which are used as a controller to call external tools, providing a feasible way to solve practical tasks.
Beyond 2:4: exploring V:N:M sparsity for efficient transformer inference on GPUs
In this study, we thoroughly investigate the application of V:N:M sparsity in vision models and LLMs across multiple tasks, from pertaining to downstream tasks.
FIRE: A Dataset for Feedback Integration and Refinement Evaluation of Multimodal Models
Vision language models (VLMs) have achieved impressive progress in diverse applications, becoming a prevalent research direction.
LV-Eval: A Balanced Long-Context Benchmark with 5 Length Levels Up to 256K
In contrast, the average context lengths of mainstream benchmarks are insufficient (5k-21k), and they suffer from potential knowledge leakage and inaccurate metrics, resulting in biased evaluation.
Structured Attention for Unsupervised Dialogue Structure Induction
Inducing a meaningful structural representation from one or a set of dialogues is a crucial but challenging task in computational linguistics.
Joint Inference of States, Robot Knowledge, and Human (False-)Beliefs
Aiming to understand how human (false-)belief--a core socio-cognitive ability--would affect human interactions with robots, this paper proposes to adopt a graphical model to unify the representation of object states, robot knowledge, and human (false-)beliefs.
PerspectiveNet: 3D Object Detection from a Single RGB Image via Perspective Points
Detecting 3D objects from a single RGB image is intrinsically ambiguous, thus requiring appropriate prior knowledge and intermediate representations as constraints to reduce the uncertainties and improve the consistencies between the 2D image plane and the 3D world coordinate.
Ranked #2 on
Monocular 3D Object Detection
on SUN RGB-D
(AP@0.15 (10 / PNet-30) metric)
Holistic++ Scene Understanding: Single-view 3D Holistic Scene Parsing and Human Pose Estimation with Human-Object Interaction and Physical Commonsense
We propose a new 3D holistic++ scene understanding problem, which jointly tackles two tasks from a single-view image: (i) holistic scene parsing and reconstruction---3D estimations of object bounding boxes, camera pose, and room layout, and (ii) 3D human pose estimation.
3D Human Pose Estimation
Human-Object Interaction Detection
+1
HUGE2: a Highly Untangled Generative-model Engine for Edge-computing
In this work, we propose a Highly Untangled Generative-model Engine for Edge-computing or HUGE2 for accelerating these two special convolutions on the edge-computing platform by decomposing the kernels and untangling these smaller convolutions by performing basic matrix multiplications.
Scene-centric Joint Parsing of Cross-view Videos
The proposed joint parsing framework represents such correlations and constraints explicitly and generates semantic scene-centric parse graphs.
