Simon DL's picture

25 8

Simon DL

SimonDL

·

Simon-dl

AI & ML interests

Reinforcement Learning

Organizations

None yet

SimonDL's activity

upvoted a paper 3 days ago

Both Text and Images Leaked! A Systematic Analysis of Multimodal LLM Data Contamination

Paper • 2411.03823 • Published 4 days ago • 41

upvoted 2 papers 11 days ago

Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning

Paper • 2410.21845 • Published 12 days ago • 10

Robots Pre-train Robots: Manipulation-Centric Robotic Representation from Large-Scale Robot Dataset

Paper • 2410.22325 • Published 12 days ago • 9

upvoted 3 papers 13 days ago

SMITE: Segment Me In TimE

Paper • 2410.18538 • Published 17 days ago • 15

MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark

Paper • 2410.19168 • Published 17 days ago • 19

ROCKET-1: Master Open-World Interaction with Visual-Temporal Context Prompting

Paper • 2410.17856 • Published 18 days ago • 48

upvoted 2 papers 18 days ago

PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction

Paper • 2410.17247 • Published 19 days ago • 43

JMMMU: A Japanese Massive Multi-discipline Multimodal Understanding Benchmark for Culture-aware Evaluation

Paper • 2410.17250 • Published 19 days ago • 12

upvoted a paper 19 days ago

Agent-to-Sim: Learning Interactive Behavior Models from Casual Longitudinal Videos

Paper • 2410.16259 • Published 20 days ago • 4

upvoted 2 papers 20 days ago

Mini-Omni2: Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities

Paper • 2410.11190 • Published 26 days ago • 20

Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation

Paper • 2410.13232 • Published 24 days ago • 40

upvoted a paper 26 days ago

Generalizable Humanoid Manipulation with Improved 3D Diffusion Policies

Paper • 2410.10803 • Published 27 days ago • 6

upvoted 6 papers about 1 month ago

Differential Transformer

Paper • 2410.05258 • Published Oct 7 • 165

NL-Eye: Abductive NLI for Images

Paper • 2410.02613 • Published Oct 3 • 22

CANVAS: Commonsense-Aware Navigation System for Intuitive Human-Robot Interaction

Paper • 2410.01273 • Published Oct 2 • 8

VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment

Paper • 2410.01679 • Published Oct 2 • 22

Helpful DoggyBot: Open-World Object Fetching using Legged Robots and Vision-Language Models

Paper • 2410.00231 • Published Sep 30 • 6

TPI-LLM: Serving 70B-scale LLMs Efficiently on Low-resource Edge Devices

Paper • 2410.00531 • Published Oct 1 • 28

upvoted a paper about 2 months ago

RACER: Rich Language-Guided Failure Recovery Policies for Imitation Learning

Paper • 2409.14674 • Published Sep 23 • 41

upvoted a paper 2 months ago

Affordance-based Robot Manipulation with Flow Matching

Paper • 2409.01083 • Published Sep 2 • 18