Papers

• Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models (2026)
  Hengyuan Zhang et al.
  1.94
• Trust Your Critic: Robust Reward Modeling and Reinforcement Learning for Faithful Image Editing and Generation (2026)
  Xiangyu Zhao et al.
  1.94
• FreeStyle: Free Control of Style-Content Dual-Reference Generation from Community LoRA Mining (2026)
  Jinghong Lan et al.
  1.94
• Agent Bazaar: Enabling Economic Alignment in Multi-Agent Marketplaces (2026)
  Seth Karten et al.
  1.89
• ETVA: Evaluation of Text-to-Video Alignment via Fine-grained Question Generation and Answering (2025)
  Kaisi Guan et al.
  1.28
• Overcoming Vocabulary Mismatch: Vocabulary-agnostic Teacher Guided Language Modeling (2025)
  Haebin Shin et al.
  1.28
• Unifying Segment Anything in Microscopy with Multimodal Large Language Model (2025)
  Manyu Li et al.
  1.28
• (Almost) Free Modality Stitching of Foundation Models (2025)
  Jaisidh Singh et al.
  1.28
• Interpretability at Scale: Identifying Causal Mechanisms in Alpaca (2023)
  Zhengxuan Wu et al.
  —
• Stream of Search (SoS): Learning to Search in Language (2024)
  Kanishk Gandhi et al.
  —
• HQ-Edit: A High-Quality Dataset for Instruction-based Image Editing (2024)
  Mude Hui et al.
  —
• Iterative Graph Alignment (2024)
  Fangyuan Yu et al.
  —
• PiTe: Pixel-Temporal Alignment for Large Video-Language Model (2024)
  Yang Liu et al.
  —
• Baichuan Alignment Technical Report (2024)
  Mingan Lin et al.
  —