pith. sign in

Emad Barsoum

Identifiers

  • name variant Emad Barsoum 0.60 · backfill

Papers (23)

  1. Pause and Think: A Dataset and Benchmark for Video-Grounded Assistive Action Suggestion cs.CV · 2026 · author #5
  2. PR2: Predictive Routing Replay for MoE-Based LLM Reinforcement Learning cs.LG · 2026 · author #10
  3. Efficient Diffusion LLMs via Temporal-Spatial Parallel Decoding and Confidence Extrapolation cs.CL · 2026 · author #6
  4. Beyond the Target: From Imitation to Collaboration in Speculative Decoding cs.CL · 2026 · author #10
  5. AgentKernelArena: Generalization-Aware Benchmarking of GPU Kernel Optimization Agents cs.CL · 2026 · author #14
  6. Theory-optimal Quantization Based on Flatness cs.LG · 2026 · author #7
  7. PARD-2: Target-Aligned Parallel Draft Model for Dual-Mode Speculative Decoding cs.CL · 2026 · author #6
  8. Long-Context Aware Upcycling: A New Frontier for Hybrid LLM Scaling cs.CL · 2026 · author #10
  9. Ego-InBetween: Generating Object State Transitions in Ego-Centric Videos cs.CV · 2026 · author #10
  10. DiffSparse: Accelerating Diffusion Transformers with Learned Token Sparsity cs.CV · 2026 · author #7
  11. DC-DiT: Adaptive Compute and Elastic Inference for Visual Generation via Dynamic Chunking cs.CV · 2026 · author #6
  12. AdaptEvolve: Improving Efficiency of Evolutionary AI Agents through Adaptive Model Selection cs.CL · 2026 · author #4
  13. Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match cs.CL · 2025 · author #9
  14. CaptionQA: Is Your Caption as Useful as the Image Itself? cs.CV · 2025 · author #6
  15. FarSkip-Collective: Unhobbling Blocking Communication in Mixture of Experts Models cs.LG · 2025 · author #6
  16. XModBench: Benchmarking Cross-Modal Capabilities and Consistency in Omni-Language Models cs.CV · 2025 · author #9
  17. DRIFT: Transferring Reasoning Priors for Efficient MLLM Fine-Tuning cs.CV · 2025 · author #9
  18. Latent Visual Reasoning cs.CV · 2025 · author #8
  19. Athena: Enhancing Multimodal Reasoning with Data-efficient Process Reward Models cs.LG · 2025 · author #6
  20. Agent Laboratory: Using LLM Agents as Research Assistants cs.HC · 2025 · author #10
  21. HP-GAN: Probabilistic 3D human motion prediction via GAN cs.CV · 2017 · author #1
  22. Training Deep Networks for Facial Expression Recognition with Crowd-Sourced Label Distribution cs.CV · 2016 · author #1
  23. Articulated Hand Pose Estimation Review cs.CV · 2016 · author #1

Mentions

  • 2606.00616 #5 · arxiv_oai · confidence 0.70 Emad Barsoum
  • 2606.00395 #10 · arxiv_oai · confidence 0.70 Emad Barsoum
  • 2605.30753 #6 · arxiv_oai · confidence 0.70 Emad Barsoum
  • 2511.11505 #6 · arxiv_oai · confidence 0.70 Emad Barsoum
  • 2506.09532 #6 · arxiv_oai · confidence 0.70 Emad Barsoum
  • 2605.24793 #10 · arxiv_oai · confidence 0.70 Emad Barsoum
  • 2605.18800 #7 · arxiv_oai · confidence 0.70 Emad Barsoum
  • 2605.16819 #14 · arxiv_oai · confidence 0.70 Emad Barsoum
  • 2501.04227 #10 · arxiv_oai · confidence 0.70 Emad Barsoum
  • 2509.24251 #8 · arxiv_oai · confidence 0.70 Emad Barsoum

Frequent Coauthors