Gholamreza Haffari

CARD: Towards Conditional Design of Multi-agent Topological Structures

G-reasoner: Foundation Models for Unified Reasoning over Graph-structured Knowledge

BEYOND IMITATION: RECOVERING DENSE REWARDS FROM DEMONSTRATIONS

SituatedThinker: Grounding LLM Reasoning with Real-World through Situated Thinking

Learning with Interaction: Agentic Distillation for Large Language Model Reasoning

Physics-Grounded Motion Forecasting via Equation Discovery for Trajectory-Guided Image-to-Video Generation

Unbiased Sliced Wasserstein Kernels for High-Quality Audio Captioning

GFM-RAG: Graph Foundation Model for Retrieval Augmented Generation

FPSAttention: Training-Aware FP8 and Sparsity Co-Design for Fast Video Diffusion

The Best of Both Worlds: Bridging Quality and Diversity in Data Selection with Bipartite Graph

Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Models

The Best of Both Worlds: Bridging Quality and Diversity in Data Selection with Bipartite Graph

Jigsaw Puzzles: Splitting Harmful Questions to Jailbreak Large Language Models in Multi-turn Interactions

ACUS: Audio Captioning with Unbiased Sliced Wasserstein Kernel

Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Models

From Corpora to Causality: Unveiling Causal Comprehension in Large Language Models

An Empirical Study on Enhancing LLMs' Alignment Capabilities through Restyled In-Context Learning Demonstration Examples

Jigsaw Puzzles: Splitting Harmful Questions to Jailbreak Large Language Models

SCAR: Efficient Instruction-Tuning for Large Language Models via Style Consistency-Aware Response Ranking

IRIS: An Iterative and Integrated Framework for Real-Time Causal Discovery