Anandharaju Durai Raju

Aggressive 4-bit quantization can cripple MLLM performance, but a novel residual reconstruction technique recovers lost capabilities with minimal overhead.

Rollout activation quantization, not training-side errors, is the hidden culprit behind FP4 RL accuracy degradation, and a clever residual correction can bridge the gap to full precision.

LLMs can be effectively combined with graph-based methods to capture both semantic and structural information in tables, leading to state-of-the-art performance in table annotation tasks.