9 papers
Quantization Beyond Uniform Bit Allocation
K. S. Sreeramji, Sabyasachi Basu, Ravishankar Krishnaswamy +2
Quantization is a fundamental technique to handle the growing sizes of embeddings generated by modern models. Existing quantization schemes are largely embedding agnostic and alloc…
On Strengths and Limitations of Single-Vector Embeddings
Archish S, Mihir Agarwal, Ankit Garg +2
Recent work (Weller et al., 2025) introduced a naturalistic dataset called LIMIT and showed empirically that a wide range of popular single-vector embedding models suffer substanti…
Chow-Liu Ordering for Long-Context Reasoning in Chain-of-Agents
Naman Gupta, Vaibhav Singh, Arun Iyer +8
Sequential multi-agent reasoning frameworks such as Chain-of-Agents (CoA) handle long-context queries by decomposing inputs into chunks and processing them sequentially using LLM-b…
Cost Efficient Fairness Audit Under Partial Feedback
Nirjhar Das, Mohit Sharma, Praharsh Nanavati +2
We study the problem of auditing the fairness of a given classifier under partial feedback, where true labels are available only for positively classified individuals, (e.g., loan…
Welfarist Formulations for Diverse Similarity Search
Siddharth Barman, Nirjhar Das, Shivam Gupta +1
Nearest Neighbor Search (NNS) is a fundamental problem in data structures with wide-ranging applications, such as web search, recommendation systems, and, more recently, retrieval-…
Incorporating Token Importance in Multi-Vector Retrieval
Archish S, Ankit Garg, Kirankumar Shiragur +1
ColBERT introduced a late interaction mechanism that independently encodes queries and documents using BERT, and computes similarity via fine-grained interactions over token-level…