Why Directly Learning Periodic Trajectories Can Fail
Research
Research News
New papers, breakthroughs and academic AI research
Quantization Thresholds Replicate, Failure Modes Do Not: A Three-Model Study of Agentic Tool Use in Polish from 8-bit to 2-bit
Research
Uncertainty-Aware Selection of Online Algorithms with Simulator Ensembles
Research
LAM: Efficient Lossy Agent Memory Framework With A Retrieval-Score Error Bound
Research
mu-bench: A Multilingual Utterance Transcription Benchmark
Research
Using LMs to Model the Effects of Context and Coreference during Sentence Comprehension
Research
ScopeIF: Improving Scope-Aware Precise Instruction-Following in Large Language Models via Graded Reward Modeling
Research
The Judge Is Not Its Twin: Post-training makes a model's writing more predictable but barely moves its taste, as a judge, toward predictable writing
Research
OptiArena: Can LLMs Improve Executable Algorithms under Fixed Resource Budgets?
Research
Phase Space Attention:A Hairer Lift Circumvents the Single-Layer Induction Obstruction
Research
AgentHabit: Characterizing Distinct Behaviors of Agents on Everyday Tasks
Research
A model of rational interlocutors: Unification of comprehension and production
Research