384 citations · 504 across the 25 of their papers we have counts for
27 papers
Learning What to Investigate Next: Meta-Reasoning for Long-Horizon Research Agents
Ankur Samanta, Yonathan Efroni, Paul Sajda +2
Long-horizon research agents must decide both how to investigate and what to investigate next as evidence accumulates. This is hard to learn because such decisions are sparse in lo…
BayesBench: Evaluating LLM Belief Trajectories Under Multi-Turn Evidence Accumulation
Ankur Samanta, Akshayaa Magesh, Tal Lancewicki +7
Large language models (LLMs) are typically deployed in multi-turn conversations, where each turn provides new evidence that should reduce epistemic uncertainty about their environm…
Credit Assignment with Resets in Language Model Reasoning
Ankur Samanta, Akshayaa Magesh, Ayush Jain +7
Contemporary reinforcement learning with verifiable reward methods post-train language models on multi-step reasoning by assigning a single outcome reward uniformly across all toke…
Multimodal Generative Recommendation for Fusing Semantic and Collaborative Signals
Moritz Vandenhirtz, Kaveh Hassani, Shervin Ghasemlou +5
Sequential recommender systems rank relevant items by modeling a user's interaction history and computing the inner product between the resulting user representation and stored ite…
Structure Enables Effective Self-Localization of Errors in LLMs
Ankur Samanta, Akshayaa Magesh, Ayush Jain +8
Self-correction in language models remains elusive. In this work, we explore whether language models can explicitly localize errors in incorrect reasoning, as a path toward buildin…
Imbalanced Gradients in RL Post-Training of Multi-Task LLMs
Runzhe Wu, Ankur Samanta, Ayush Jain +7
Multi-task post-training of large language models (LLMs) is typically performed by mixing datasets from different tasks and optimizing them jointly. This approach implicitly assume…
Self-Improvement of Language Models by Post-Training on Multi-Agent Debate
Ankur Samanta, Akshayaa Magesh, Runzhe Wu +7
Self-improvement, where models improve beyond their current performance without external supervision, remains a challenge. The core difficulty is sourcing a training signal stronge…
Generating Long Semantic IDs in Parallel for Recommendation
Yupeng Hou, Jiacheng Li, Ashley Shin +6
Semantic ID-based recommendation models tokenize each item into a small number of discrete tokens that preserve specific semantics, leading to better performance, scalability, and…
Higher-order Structure Boosts Link Prediction on Temporal Graphs
Jingzhe Liu, Zhigang Hua, Yan Xie +5
Temporal Graph Neural Networks (TGNNs) have gained growing attention for modeling and predicting structures in temporal graphs. However, existing TGNNs primarily focus on pairwise…
Unifying Generative and Dense Retrieval for Sequential Recommendation
Liu Yang, Fabian Paischer, Kaveh Hassani +11
Sequential dense retrieval models utilize advanced sequence learning techniques to compute item and user representations, which are then used to rank relevant items for a user thro…
Preference Discerning with LLM-Enhanced Generative Retrieval
Fabian Paischer, Liu Yang, Linfeng Liu +12
In sequential recommendation, models recommend items based on user's interaction history. To this end, current models usually incorporate information such as item descriptions and…
Learning Graph Quantized Tokenizers
Limei Wang, Kaveh Hassani, Si Zhang +7
Transformers serve as the backbone architectures of Foundational Models, where domain-specific tokenizers allow them to adapt to various domains. Graph Transformers (GTs) have rece…
How to Make LMs Strong Node Classifiers?
Zhe Xu, Kaveh Hassani, Si Zhang +7
Language Models (LMs) are increasingly challenging the dominance of domain-specific models, such as Graph Neural Networks (GNNs) and Graph Transformers (GTs), in graph learning tas…
Rankitect: Ranking Architecture Search Battling World-class Engineers at Meta Scale
Wei Wen, Kuang-Hung Liu, Igor Fedorov +19
Neural Architecture Search (NAS) has demonstrated its efficacy in computer vision and potential for ranking systems. However, prior work focused on academic problems, which are eva…
MVMTnet: A Multi-variate Multi-modal Transformer for Multi-class Classification of Cardiac Irregularities Using ECG Waveforms and Clinical Notes
Ankur Samanta, Mark Karlov, Meghna Ravikumar +3
Deep learning provides an excellent avenue for optimizing diagnosis and patient monitoring for clinical-based applications, which can critically enhance the response time to the on…
Material Prediction for Design Automation Using Graph Representation Learning
Shijie Bian, Daniele Grandi, Kaveh Hassani +8
Successful material selection is critical in designing and manufacturing products for design automation. Designers leverage their knowledge and experience to create high-quality de…
Evaluating Graph Generative Models with Contrastively Learned Features
Hamed Shirzad, Kaveh Hassani, Danica J. Sutherland
A wide range of models have been proposed for Graph Generative Models, necessitating effective methods to evaluate their quality. So far, most techniques use either traditional met…
Learning Graph Augmentations to Learn Graph Representations
Kaveh Hassani, Amir Hosein Khasahmadi
Devising augmentations for graph contrastive learning is challenging due to their irregular structure, drastic distribution shifts, and nonequivalent feature spaces across datasets…
Cross-Domain Few-Shot Graph Classification
Kaveh Hassani
We study the problem of few-shot graph classification across domains with nonequivalent feature spaces by introducing three new cross-domain benchmarks constructed from publicly av…
Classifying Component Function in Product Assemblies with Graph Neural Networks
Vincenzo Ferrero, Kaveh Hassani, Daniele Grandi +1
Function is defined as the ensemble of tasks that enable the product to complete the designed purpose. Functional tools, such as functional modeling, offer decision guidance in the…
PointMask: Towards Interpretable and Bias-Resilient Point Cloud Processing
Saeid Asgari Taghanaki, Kaveh Hassani, Pradeep Kumar Jayaraman +2
Deep classifiers tend to associate a few discriminative input variables with their objective function, which in turn, may hurt their generalization capabilities. To address this, o…
Contrastive Multi-View Representation Learning on Graphs
Kaveh Hassani, Amir Hosein Khasahmadi
We introduce a self-supervised approach for learning node and graph level representations by contrasting structural views of graphs. We show that unlike visual representation learn…
Memory-Based Graph Networks
Amir Hosein Khasahmadi, Kaveh Hassani, Parsa Moradi +2
Graph neural networks (GNNs) are a class of deep models that operate on data with arbitrary topology represented as graphs. We introduce an efficient memory layer for GNNs that can…
Relational Graph Representation Learning for Open-Domain Question Answering
Salvatore Vivona, Kaveh Hassani
We introduce a relational graph neural network with bi-directional attention mechanism and hierarchical representation learning for open-domain question answering task. Our model c…