PPaperPicks

Emad Barsoum

27 papers at tracked venues · 22 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. AdaptEvolve: Improving Efficiency of Evolutionary AI Agents through Adaptive Model Selection
  2. DRIFT: Transferring Reasoning Priors for Efficient MLLM Fine-Tuning
  3. DiffBench Meets DiffAgent: End-to-End LLM-Driven Diffusion Acceleration Code Generation
  4. Learnable Permutation for Structured Sparsity on Transformer Models
  5. MoEC: A Memory-Routed Mixture-of-Experts Controller for Adaptive Minecraft Control
  6. SparK: Query-Aware Unstructured Sparsity with Recoverable KV Cache Channel Pruning
  7. Theory-optimal Quantization Based on Flatness
  8. Agent Laboratory: Using LLM Agents as Research Assistants
  9. Amphista: Bi-directional Multi-head Decoding for Accelerating LLM Inference
  10. EGSRAL: An Enhanced 3D Gaussian Splatting Based Renderer with Automated Labeling for Large-Scale Driving Scene
  11. Gumiho: A Hybrid Architecture to Prioritize Early Tokens in Speculative Decoding
  12. ReNeg: Learning Negative Embedding with Reward Guidance
  13. Self-Taught Agentic Long Context Understanding
  14. SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer
  15. TTT-Bench: A Benchmark for Evaluating Reasoning Ability with Simple and Novel Tic-Tac-Toe-style Games
  16. TaDA: Training-free recipe for Decoding with Adaptive KV Cache Compression and Mean-centering
  17. Týr-the-Pruner: Structural Pruning LLMs via Global Sparsity Distribution Optimization
  18. Unleashing Hour-Scale Video Training for Long Video-Language Understanding
  19. Zebra-Llama: Towards Extremely Efficient Hybrid Models
  20. Customizing Text-to-Image Generation with Inverted Interaction
  21. DL-QAT: Weight-Decomposed Low-Rank Quantization-Aware Training for Large Language Models
  22. DiP-GO: A Diffusion Pruner via Few-step Gradient Optimization
  23. Enhancing Vision Transformer: Amplifying Non-Linearity in Feedforward Network Module
  24. MonoGS++: Fast and Accurate Monocular RGB Gaussian SLAM
  25. QT-ViT: Improving Linear Attention in ViT with Quadratic Taylor Expansion
  26. Taming Diffusion Prior for Image Super-Resolution with Domain Shift SDEs
  27. The Ninth NTIRE 2024 Efficient Super-Resolution Challenge Report