Yftah Ziser

Venues

Frequent coauthors

Papers

1. Aligning What LLMs Do and Say: Towards Self-Consistent Explanations
   ACL 2026 ·

   Sahar Admoni

   DBLP profile ↗ORCID search ↗
2. Beyond Next Token Probabilities: Learnable, Fast Detection of Hallucinations and Data Contamination on LLM Output Distributions
   AAAI 2026 ·

   Guy Bar-Shalom

   DBLP profile ↗ORCID search ↗
3. Can VLMs Predict Future States? Bootstrapping World Models from Inverse Dynamics
   ACL 2026 ·

   Yifu Qiu

   DBLP profile ↗ORCID search ↗
4. A Simple Yet Effective Method for Non-Refusing Context Relevant Fine-grained Safety Steering in LLMs
   EMNLP 2025 ·

   Shaona Ghosh

   DBLP profile ↗ORCID search ↗
5. Beyond Token Probes: Hallucination Detection via Activation Tensors with ACT-ViT
   NeurIPS 2025 ·

   Guy Bar-Shalom

   DBLP profile ↗ORCID search ↗
6. Iterative Multilingual Spectral Attribute Erasure
   EMNLP 2025 ·

   Shun Shao

   DBLP profile ↗ORCID search ↗
7. Knowing Before Saying: LLM Representations Encode Information About Chain-of-Thought Success Before Completion
   ACL 2025 ·

   Anum Afzal

   DBLP profile ↗ORCID search ↗
8. Policy Optimized Text-to-Image Pipeline Design
   NeurIPS 2025 ·

   Uri Gadot

   DBLP profile ↗ORCID search ↗
9. TSPRank: Bridging Pairwise and Listwise Methods with a Bilinear Travelling Salesman Model
   SIGKDD 2025 ·

   Weixian Waylon Li

   DBLP profile ↗ORCID search ↗
10. Are Large Language Model Temporally Grounded?
    NAACL 2024 ·

    Yifu Qiu

    DBLP profile ↗ORCID search ↗
11. Layer by Layer: Uncovering Where Multi-Task Learning Happens in Instruction-Tuned Large Language Models
    EMNLP 2024 ·

    Zheng Zhao

    DBLP profile ↗ORCID search ↗
12. Spectral Editing of Activations for Large Language Model Alignment
    NeurIPS 2024 ·

    Yifu Qiu

    DBLP profile ↗ORCID search ↗