Add EMNLP paper

source/_data/SymbioticLab.bib

@@ -2612,3 +2612,17 @@ @InProceedings{gputogrid:powerup26
 While the rapid expansion of data centers poses challenges for power grids, it also offers new opportunities as flexible loads. Existing power system research often abstracts data centers as aggregate resources, while computer system research focuses on GPU energy efficiency and largely ignores grid impacts. To bridge this gap, we develop a GPU-to-Grid framework that couples device-level GPU control with power system objectives. We study distribution-level voltage regulation enabled by LLM inference flexibility, using batch size as a data-center-side control knob that trades off GPU power consumption, inference latency, and token throughput. We first formulate the problem as an optimization problem and then realize it as an online feedback optimization controller, implemented by the data center operator using its own empirical GPU power-performance model and real-time measurements from both the GPU and grid systems. Our key insight is that reducing GPU power alleviates lower-voltage violations, while increasing GPU power mitigates upper-voltage violations; this challenges the common belief that minimizing GPU power is always beneficial to power grids.
   }
 }
+
+@InProceedings{langenergy:emnlp26,
+  author          = {Naihao Deng and Alissa Shen and Yiming Feng and Joan Nwatu and Jae-Won Chung and Mosharaf Chowdhury and Yulong Chen and Rada Mihalcea},
+  title           = {The Language-Energy Divide: Measuring Energy Costs of Multilingual {LLM} Inference},
+  booktitle       = {EMNLP Main Conference},
+  year            = {2026},
+  month           = {Oct},
+  publist_confkey = {EMNLP'26},
+  publist_link    = {paper || langenergy-emnlp26.pdf},
+  publist_topic   = {Energy-Efficient Systems},
+  publist_abstract = {
+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.
+  }
+}

source/publications/index.md

@@ -492,6 +492,14 @@ venues:
         name: ACM Conference on AI and Agentic Systems Demo Track
         date: 2026-05-26
         url: https://caisconf.org
+  EMNLP:
+    category: Conferences
+    occurrences:
+      - key: EMNLP'26
+        name: The 2026 Conference on Empirical Methods in Natural Language Processing
+        date: 2026-10-25
+        url: https://2026.emnlp.org/
+        acceptance: 15.4%
   ACL:
     category: Conferences
     occurrences: