Devi Pratama

devi-pp's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 1 day ago

ParetoSaddler: Pareto-Guided Optimization of Agent Harnesses for Quality and Cost

Paper • 2611.02079 • Published 6 days ago • 19

upvoted a paper 7 days ago

OmniShowcase: Omnidirectional Subject-Consistent Video Generation from Multi-View Images

Paper • 2610.35684 • Published 12 days ago • 60

upvoted a paper 12 days ago

Deep Search in Real-World Web Environments

Paper • 2610.30181 • Published 19 days ago • 108

upvoted a paper 14 days ago

Think Harder Where It Matters: Item-Level Adaptive Recursion for Sequential Recommendation

Paper • 2610.30128 • Published 17 days ago • 9

upvoted a paper 17 days ago

SCOPE: Semantic Bounded Credit Optimization for Prompt Engineering in Text-to-image Generation

Paper • 2610.22264 • Published 23 days ago • 32

upvoted a paper 23 days ago

Stateless Language Agents: Scaling Long-Horizon Automated Research

Paper • 2610.07625 • Published Oct 6 • 16

upvoted a paper 24 days ago

Hear the World in Stereo: Learning Dynamic Spatial Correspondence for Immersive Joint Video-Audio Generation

Paper • 2609.38748 • Published about 1 month ago • 52

upvoted a paper 25 days ago

In-context Robot Learning Made Simple: A Democratized Recipe for Manipulation Tasks

Paper • 2609.38173 • Published Sep 29 • 48

upvoted a paper 30 days ago

Memadapter: Counterfactual Adaptation Against Memory-induced Sycophancy

Paper • 2610.05162 • Published Oct 4 • 49

upvoted 5 papers about 1 month ago

From Gradients to Capabilities: Understanding Multi-Teacher On-Policy Distillation

Paper • 2610.02179 • Published Oct 1 • 7

Disaggregated Quantization: Specializing LLM Prefill and Decode

Paper • 2609.26333 • Published Sep 22 • 83

Blaming Across the Aisle: Political Contrasting and Blame Attribution in the Danish Parliament

Paper • 2609.26346 • Published Sep 22 • 7

Document Retrieval-Aware Chunking (D-RAC): Universal Retrieval-Aware Ingestion of Enterprise Documents via PDF Normalization and Multimodal Markdown Conversion

Paper • 2609.24220 • Published Sep 21 • 49

CADWorld: Computer-Use Benchmark for Long-Horizon Computer-Aided Design

Paper • 2609.16251 • Published Sep 14 • 10

upvoted 6 papers about 2 months ago

LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence

Paper • 2609.17488 • Published Sep 15 • 270

StudentSim: Training LLM-based Student Simulators

Paper • 2609.01591 • Published Sep 1 • 153

Continual Learning Mechanisms Compose for Long-Horizon Memorization

Paper • 2609.06986 • Published Sep 7 • 49

StepAudio 3 Gen Technical Report

Paper • 2609.12945 • Published Sep 11 • 96

StepAudio 3 Music Technical Report

Paper • 2609.16034 • Published Sep 11 • 90

StepAudio 3 Realtime Technical Report

Paper • 2609.14005 • Published Sep 12 • 110