Papers by Aditya Grover
Enabling Autoregressive Models to Fill In Masked Tokens (2026.findings-eacl)
Copied to clipboard
| Challenge: | Autoregressive (AR) and masked language modeling (MLM) models are incapable of mucked infilling, which is the ability to predict mangled tokens between past and future context. |
| Approach: | They propose a method that leverages the strengths of autoregressive and masked language modeling to achieve state-of-the-art mucked infilling performance. |
| Outcome: | The proposed approach outperforms existing methods on masked infilling tasks. |
The Pitfalls of KV Cache Compression (2026.acl-long)
Copied to clipboard
| Challenge: | Recent literature has shown minimal degradation of KV cache in multi-instruction prompts . authors show that certain instructions degrade much more rapidly with compression . |
| Approach: | They propose to change KV cache eviction policies to reduce the impact of KV evict bias . they propose to use a 'simple' evviction policy to reduce ejection bias if the LLM is a multi-instruction model . |
| Outcome: | The proposed methods show that certain instructions degrade much faster with compression, causing them to be ignored by the LLM. |
InstructAny2Pix: Image Editing with Multi-Modal Prompts (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing image editing methods struggle with complex instructions involving multiple objects or reference images. |
| Approach: | They propose a novel image editing model that leverages a multi-modal LLM to execute complex edit instructions. |
| Outcome: | The proposed model outperforms existing models and benchmarks in two multi-modal datasets. |
Comparing Bad Apples to Good Oranges Aligning Large Language Models via Joint Preference Optimization (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent studies have shown that acquiring human preferences by comparing generations is not effective for large language models. |
| Approach: | They propose a preference optimization objective that elicits preferences jointly over the instruction-response pairs. |
| Outcome: | The proposed approach outperforms prior preference optimizations by 5.2% and 3.3% in summarization and open-ended dialogue datasets. |