Bailin Wang

GenSim: Generating Robotic Simulation Tasks via Large Language Models

Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement

Parallelizing Linear Transformers with the Delta Rule over Sequence Length

Lemur: Harmonizing Natural Language and Code for Language Agents

Gated Slot Attention for Efficient Linear-Time Sequence Modeling

MR-Ben: A Meta-Reasoning Benchmark for Evaluating System-2 Thinking in LLMs

Bias Amplification in Language Model Evolution: An Iterated Learning Perspective

Structured Fine-Tuning Enables Data-Efficient Adaptation of Code Language Models