Add Kairos paper.

source/_data/SymbioticLab.bib

@@ -768,7 +768,7 @@ @InProceedings{hydra:fast22
 
 @InProceedings{tpp:asplos23,
   author    = {Hasan Al Maruf and Hao Wang and Abhishek Dhanotia and Johannes Weiner and Niket Agarwal and Pallab Bhattacharya and Chris Petersen and Mosharaf Chowdhury and Shobhit Kanaujia and Prakash Chauhan},
-  booktitle = {ASPLOS},
+  booktitle = {ACM ASPLOS},
   title     = {{TPP}: Transparent Page Placement for {CXL}-Enabled Tiered-Memory},
   year      = {2023},
 
@@ -2118,7 +2118,7 @@ @Article{tetriserve:arxiv25
 
 @InProceedings{tetriserve:asplos26,
   author          = {Runyu Lu and Shiqi He and Wenxuan Tan and Shenggui Li and Ruofan Wu and Jeff J. Ma and Ang Chen and Mosharaf Chowdhury},
-  booktitle       = {ASPLOS},
+  booktitle       = {ACM ASPLOS},
   title           = {{TetriServe}: Efficiently Serving Mixed {DiT} Workloads},
   year            = {2026},
   month           = {March},
@@ -2626,3 +2626,20 @@ @InProceedings{langenergy:emnlp26
 Large language models (LLMs) are increasingly deployed in multilingual settings, yet the energy costs of serving these models across different languages remain poorly understood. We present a systematic study of inference energy consumption across languages with ML.Energy framework. We find striking disparities: energy consumption per output token varies by up to 8.3x across languages, while total energy for a fixed set of requests varies by up to 179x between the cheapest (English, 17.6 kJ) and the most expensive (Pashto, 3,147 kJ) languages. Our analysis shows that this disparity is driven by two compounding factors: (1) higher per-token energy costs for languages using complex or rare scripts, and (2) more tokens generated for low-resource languages. Moreover, we find a double cost + performance penalty: languages with the highest energy footprints also tend to achieve the lowest task accuracy. We reveal that the energy divide persists across models, hardware, and tasks, suggesting a systemic energy inequity in multilingual LLM deployment. Finally, we recommend that the community treat energy as a first-class evaluation axis, extend reporting checklists and model cards to include it, and adopt deployment-side mitigations for better energy efficiency.
   }
 }
+
+@InProceedings{kairos:asplos27,
+  author          = {Yichao Yuan and Mosharaf Chowdhury and Nishil Talati},
+  booktitle       = {ACM ASPLOS},
+  title           = {{KAIROS}: Stateful, Context-Aware Power-Efficient Agentic Inference Serving},
+  year            = {2027},
+  month           = {Apr},
+  publist_confkey = {ASPLOS'27},
+  publist_link    = {paper || kairos-asplos27.pdf},
+  publist_topic   = {Systems + AI},
+  publist_topic   = {Energy-Efficient Systems},
+  publist_abstract = {
+Power has become a central bottleneck for AI inference. This problem is becoming more urgent as agentic AI emerges as a major workload class, yet prior power-management techniques focus almost entirely on single-turn LLM serving. Our analysis shows that agentic serving behaves fundamentally differently: each request carries long-lived context that evolves across tool-interleaved turns, and lowering GPU frequency can push the system into a thrashing regime where memory pressure sharply worsens both performance and power efficiency. These observations show that power optimization for agentic serving requires rethinking.
+
+We present KAIROS, a context-aware power optimization system for agentic AI serving. KAIROS uses agent context as a first-class control signal to jointly manage GPU frequency, per-instance concurrency, and multi-instance request placement. This enables KAIROS to save power when memory headroom exists while avoiding thrashing and preserving performance targets. At a high level, KAIROS tracks requests at agent granularity, adapts local control to context growth and agent progress, and routes agents across instances to jointly improve power efficiency and memory stability. Evaluated across diverse software and data engineering agentic tasks, KAIROS achieves an average of 27% (up to 39.8%) power reduction while meeting the performance targets.
+  }
+}

source/_posts/Kairos-Accepted-to-Appear-at-ASPLOS-27.md

@@ -1,5 +1,5 @@
 ---
-title: Kairos Accepted to Appear at ASPLOS'27
+title: KAIROS Accepted to Appear at ASPLOS'27
 categories:
   - News
 date: 2026-07-31 17:54:49

source/publications/index.md

@@ -116,15 +116,19 @@ venues:
   ASPLOS:
     category: Conferences
     occurrences:
+    - key: ASPLOS'27
+      name: The 32nd ACM International Conference on Architectural Support for Programming Languages and Operating Systems
+      date: 2027-04-11
+      url: https://www.asplos-conference.org/asplos2027/
     - key: ASPLOS'26
       name: The 31st ACM International Conference on Architectural Support for Programming Languages and Operating Systems
       date: 2026-03-22
-      url: https://asplos-conference.org/2026/
+      url: https://www.asplos-conference.org/asplos2026/
       acceptance: 15.71%
     - key: ASPLOS'23
       name: The 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems
       date: 2023-03-25
-      url: https://asplos-conference.org/2023/
+      url: https://asplos-conference.org/asplos2023/
       acceptance: 26.67%
   SIGMETRICS:
     category: Conferences