Papers by Tianjun Zhang
Mirroring Users: Towards Building Preference-aligned User Simulator with User Feedback in Recommendation (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models lack specific task alignment and large-scale simulations are challenging due to their ambiguity, noise and massive volume. |
| Approach: | They propose a framework that leverages user feedback in RSs with advanced LLM capabilities to generate high-quality simulation data. |
| Outcome: | The proposed framework boosts the alignment with human preferences and in-domain reasoning capabilities of the fine-tuned LLMs. |
Learning from Mistakes: Iterative Prompt Relabeling for Text-to-Image Diffusion Model Training (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Recent advances in diffusion models have shown impressive performance in many domains, but their ability to follow instructions is still unsatisfactory. |
| Approach: | They propose an algorithm that aligns images to text through iterative image sampling and prompt relabeling with feedback. |
| Outcome: | The proposed algorithm improves on the spatial relation VISOR benchmark by 15.22% compared to previous methods. |
Adaptive and Representative Multi-Interest Modeling for Recommendation with Large Language Model (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for multi-interest analysis of users rely on heuristic assumptions . however, the granularity of raw generation of LLMs is agnostic, leading to overly fine or coarse interest grouping. |
| Approach: | They propose an LLM-driven adaptive and representative multi-interest modeling framework that exploits the agnostic granularity of LLMs for multi-interest analysis. |
| Outcome: | The proposed model outperforms baselines on real-world datasets. |
LLoCO: Learning Long Contexts Offline (2024.emnlp-main)
Copied to clipboard
Sijun Tan, Xiuyu Li, Shishir G Patil, Ziyang Wu, Tianjun Zhang, Kurt Keutzer, Joseph Gonzalez, Raluca Popa
| Challenge: | Large language models are still unable to handle long contexts due to the quadratic computational and memory overhead of the self-attention mechanism and the substantial KV cache sizes during generation. |
| Approach: | They propose a method to learn contexts offline through context compression and in-domain parameter-efficient finetuning with LoRA. |
| Outcome: | The proposed model outperforms in-context learning while using 30 fewer tokens during inference and significantly reduces the cost of long document question answering. |
TopoDIM: One-shot Topology Generation of Diverse Interaction Modes for Multi-Agent Systems (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing communication topologies rely on spatio-temporal dialogues, which incur high latency and computation. |
| Approach: | They propose a framework for one-shot Topology generation with Diverse Interaction Modes that enables agents to construct heterogeneous communication without iterative coordination. |
| Outcome: | The proposed framework reduces total token consumption by 46.41% while improving average performance by 1.50% over state-of-the-art methods. |
Contrastive Code Representation Learning (2021.emnlp-main)
Copied to clipboard
| Challenge: | Recent work learns contextual representations of source code by reconstructing tokens from their context. |
| Approach: | They propose a contrastive pre-training task that learns code functionality, not form . they propose scalable compilers that can generate variants of a program . |
| Outcome: | The proposed task outperforms RoBERTa on an adversarial code clone detection benchmark by 39% AUROC. |