6 papers
Evolutionary Multi-Task Optimization for LLM-Guided Program Discovery
Halil Alperen Gozeten, Xuechen Zhang, Emrullah Ildiz +3
Recent LLM-guided evolutionary search methods have shown that iterative program mutation can discover strong algorithms, but they typically optimize each task independently, even w…
MUX: Continuous Reasoning via Multiplexed Tokens
Ayhan Suleymanzade, Halil Alperen Gozeten, Michael Bronstein +2
Language models solve complex problems by articulating intermediate reasoning steps in natural language. While effective, this process is computationally bottlenecked: each reasoni…
Learning to Correct: Calibrated Reinforcement Learning for Multi-Attempt Chain-of-Thought
Muhammed Emrullah Ildiz, Halil Alperen Gozeten, Ege Onur Taga +1
State-of-the-art reasoning models utilize long chain-of-thought (CoT) to solve increasingly complex problems using more test-time computation. In this work, we explore a long CoT s…
Continuous Chain of Thought Enables Parallel Exploration and Reasoning
Halil Alperen Gozeten, M. Emrullah Ildiz, Xuechen Zhang +3
Modern language models generate chain-of-thought traces by autoregressively sampling tokens from a finite vocabulary. While this discrete sampling has achieved remarkable success,…
Test-Time Training Provably Improves Transformers as In-context Learners
Halil Alperen Gozeten, M. Emrullah Ildiz, Xuechen Zhang +3
Test-time training (TTT) methods explicitly update the weights of a model to adapt to the specific test instance, and they have found success in a variety of settings, including mo…
High-dimensional Analysis of Knowledge Distillation: Weak-to-Strong Generalization and Scaling Laws
M. Emrullah Ildiz, Halil Alperen Gozeten, Ege Onur Taga +2
A growing number of machine learning scenarios rely on knowledge distillation where one uses the output of a surrogate model as labels to supervise the training of a target model.…