8 papers
What Do Verifiable Rewards Teach Video-Language Models About Time? A Controlled Multi-Model Study
Avyay Sadhu, Patrick Cooper
Reinforcement learning from verifiable rewards (RLVR) has produced large reasoning gains in language models, and verifiable video benchmarks make it applicable to causal-temporal v…
Expected Free Energy as Belief-Dependent Utility for rho-POMDPs
Patrick Cooper, Alvaro Velasquez
An agent acting under partial observability must decide when to gather information and which observations are worth their cost. Standard POMDPs value information only through its e…
Narration-of-Thought: Inference-Time Scaffolding for Defeasible Ethical Reasoning in Large Language Models
Patrick Cooper, Alvaro Velasquez
Standard chain-of-thought on moral dilemmas exhibits two failure modes: stakeholder collapse (the trace names at most one party with a stake in the outcome) and uncertainty suppres…
DeFAb: A Dataset for Grounded Scientific Discovery through Defeasible Abduction
Patrick Cooper, Alvaro Velasquez, Avyay Sadhu
A theory can accommodate a counterexample by adding an exception. The harder problem is deciding how far the exception should extend and which predictions should survive. We presen…
KV-Fold: One-Step KV-Cache Recurrence for Long-Context Inference
Alireza Nadali, Patrick Cooper, Ashutosh Trivedi +1
We introduce KV-Fold, a simple, training-free long-context inference protocol that treats the key-value (KV) cache as the accumulator in a left fold over sequence chunks. At each s…
Monotonicity as an Architectural Bias for Robust Language Models
Patrick Cooper, Alireza Nadali, Ashutosh Trivedi +1
Large language models (LLMs) are known to exhibit brittle behavior under adversarial prompts and jailbreak attacks, even after extensive alignment and fine-tuning. This fragility r…
Active Causal Experimentalist (ACE): Learning Intervention Strategies via Direct Preference Optimization
Patrick Cooper, Alvaro Velasquez
Discovering causal relationships requires controlled experiments, but experimentalists face a sequential decision problem: each intervention reveals information that should inform…
CogExplore: Contextual Exploration with Language-Encoded Environment Representations
Harel Biggie, Patrick Cooper, Doncey Albin +2
Integrating language models into robotic exploration frameworks improves performance in unmapped environments by providing the ability to reason over semantic groundings, contextua…