5 papers
Beyond Accuracy: Behavioral Dynamics of Agentic Multi-Hunk Repair
Noor Nashid, Daniel Ding, Keheliya Gallaba +2
Automated program repair has traditionally focused on single-hunk defects, overlooking multi-hunk bugs that are prevalent in real-world systems. Repairing these bugs requires coord…
Presynthesis: Towards Scaling Up Program Synthesis with Finer-Grained Abstract Semantics
Rui Dong, Qingyue Wu, Danny Ding +3
Abstract semantics has proven to be instrumental for accelerating search-based program synthesis, by enabling the sound pruning of a set of incorrect programs (without enumerating…
Choose, Don't Label: Multiple-Choice Query Synthesis for Program Disambiguation
Celeste Barnaby, Danny Ding, Osbert Bastani +1
High-level specifications of code are inherently ambiguous, and prior systems have explored interactive techniques to help users clarify their intent and resolve such ambiguities.…
Characterizing Multi-Hunk Patches: Divergence, Proximity, and LLM Repair Challenges
Noor Nashid, Daniel Ding, Keheliya Gallaba +2
Multi-hunk bugs, where fixes span disjoint regions of code, are common in practice, yet remain underrepresented in automated repair. Existing techniques and benchmarks pre-dominant…
NMPC and Deep Learning-Based Vibration Control of Satellite Beam Antenna Dynamics Using PZT Actuators and Sensors
Sean Kalaycioglu, Daniel Ding
This paper presents a novel approach for vibration control of satellite-based flexible beam-type antennas using Nonlinear Model Predictive Control (NMPC) and Deep Learning techniqu…