Publications

1. Test-Time Adaptation via Many-Shot Prompting: Benefits, Limits, and Pitfalls
   [Paper Link][Workshop Link]
   ICLR 2026 Workshop on AI with Recursive Self-Improvement
2. Cross-Family Speculative Prefill: Training-Free Long-Context Compression with Small Draft Models
   [Paper Link][Workshop Link]
   ICLR 2026 Workshop on AI with Recursive Self-Improvement
3. Learning What to Learn: Curriculum Curation for Test-Time Agent Learning
   [Paper Link][Workshop Link]
   ICLR 2026 Workshop on Memory for LLM-Based Agentic Systems
4. The Limits of Long-Context Reasoning in Automated Bug Fixing
   [Paper Link][Workshop Link]
   ICLR 2026 Workshop on I Can't Believe It's Not Better: Where Large Language Models Need to Improve
5. Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models
   [Paper Link]
   ICLR 2026
6. SnapStream: Efficient Long Sequence Decoding on Dataflow Accelerators
   [Paper Link]
   ISC High Performance 2026
7. LLMs Know What to Drop: Self-Attention Guided KV Cache Eviction for Efficient Long-Context Inference
   [Paper Link][Workshop Link]
   ICLR 2025 Workshop on Sparsity in LLMs (SLLM)
8. Empirical study of soft clustering technique for determining click through rate in online advertising
   [Paper Link]
   ICDMAI 2019