Strong Inapproximability for a Promise Rank Problem

Get full text

Feedback Set Problems on Bounded-Degree (Planar) Graphs

Get full text

Enhancing Instruction Prefetching via Cache and TLB Management

Get full text

From Innermost to Full Probabilistic Term Rewriting: Almost-Sure Termination, Complexity, and Modularity

Get full text

Heterogeneous SoC Integrating an Open-Source Recurrent SNN Accelerator for Neuromorphic Edge Computing on FPGA

Get full text

Improving the Performance and Learning Stability of Parallelizable RNNs Designed for Ultra-Low Power Applications

Get full text

Sieve: Dynamic Expert-Aware PIM Acceleration for Evolving Mixture-of-Experts Models

Get full text

ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents

Get full text

Reward Hacking in Rubric-Based Reinforcement Learning

Get full text

CAAFC: Chronological Actionable Automated Fact-Checker for misinformation / non-factual hallucination detection and correction

Get full text

Formalize, Don't Optimize: The Heuristic Trap in LLM-Generated Combinatorial Solvers

Get full text

Semantic Reward Collapse and the Preservation of Epistemic Integrity in Adaptive AI Systems

Get full text

OGLS-SD: On-Policy Self-Distillation with Outcome-Guided Logit Steering for LLM Reasoning

Get full text

Detecting overfitting in Neural Networks during long-horizon grokking using Random Matrix Theory

Get full text

Data-Aware Hybrid Tableaux

Get full text

Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training

Get full text

Discrete Flow Matching for Offline-to-Online Reinforcement Learning

Get full text

ProfiliTable: Profiling-Driven Tabular Data Processing via Agentic Workflows

Get full text

Agent-Based Post-Hoc Correction of Agricultural Yield Forecasts

Get full text

Hardness Amplification for (Sparse) LPN

Get full text