works on

From the 1 of 6 linked papers with an AI index.

collaborators

6 papers

cs.LG2026

-OPSD: Deriving with Policy Optimization, Training with Self-Distillation

Jiawei Xu, Minghui Liu, Juzheng Zhang +2

The paper proposes β‑OPSD, a generalized on‑policy self‑distillation method that treats the KL regularization weight as a tunable parameter, enabling a controlled interpolation bet…

cs.LG2026

The Hidden Bias of Process Reward Models:PRISM for Rewarding the Right Reasoning

Aakriti Agrawal, Souradip Chakraborty, Armin Saghafian +6

Process Reward Models (PRMs) improve credit assignment for reasoning by providing step-level feedback. However, we identify a hidden bias in PRMs caused by severe imbalance in step…

cs.LG2026

VeriGate: Verifier-Gated Step-Level Supervision for GRPO

Aakriti Agrawal, Minghui Liu, Furong Huang

Group Relative Policy Optimization (GRPO) is an effective recipe for training reasoning models with verifier-based outcome rewards, but its supervision is sparse: when all sampled…

cs.LG2026

Bridging the Divide: End-to-End Sequence-Graph Learning

Yuen Chen, Yulun Wu, Samuel Sharpe +5

Many real-world prediction tasks, particularly those involving entities such as customers or patients, involve both {sequential} and {relational} data. Each entity maintains its ow…

cs.AI2026

TimeSqueeze: Dynamic Patching for Efficient Time Series Forecasting

Sravan Kumar Ankireddy, Nikita Seleznev, Nam H. Nguyen +4

Transformer-based time series foundation models face a fundamental trade-off in choice of tokenization: point-wise embeddings preserve temporal fidelity but scale poorly with seque…

cs.LG2026

PersonaLedger: Generating Realistic Financial Transactions with Persona Conditioned LLMs and Rule Grounded Feedback

Dehao Yuan, Tyler Farnan, Stefan Tesliuc +8

Strict privacy regulations limit access to real transaction data, slowing open research in financial AI. Synthetic data can bridge this gap, but existing generators do not jointly…