activity
20242026
collaborators

8 papers

cs.LG2026

Parameter-free Adaptive Sparse Attention via Compression-Based Content Selection

Debarshi Kundu, Swaroop Ghosh, Vasant Honavar

Data-adaptive sparse attention masks substantially outperform fixed patterns (e.g., BigBird and Longformer) and can even exceed dense attention on long sequences. Existing adaptive…

cs.LG2026

Restoring the Sweet Spot: Pass-Rate Weighted Self-Distillation for LLM Reasoning

Zehao Liu, Yuanpu Cao, Jinghui Chen +1

Self-Distillation Policy Optimization (SDPO) provides dense token-level credit assignment for reinforcement learning with large language models by leveraging the model's own feedba…

cs.LG2026

Projection-Free Transformers via Gaussian Kernel Attention

Debarshi Kundu, Archisman Ghosh, Swaroop Ghosh +1

Self-attention in Transformers is typically implemented as , where , , and are learned linear projections of the input…

cs.CV2026

Hyperdimensional Cross-Modal Alignment of Frozen Language and Image Models for Efficient Image Captioning

Abhishek Dalvi, Vasant Honavar

Large unimodal foundation models for vision and language encode rich semantic structures, yet aligning them typically requires computationally intensive multimodal fine-tuning. Suc…

cs.LG2026

Simple Denoising Diffusion Language Models

Huaisheng Zhu, Zhengyu Chen, Shijie Zhou +8

Recent Uniform State Diffusion Models (USDMs), initialized from a uniform prior, offer the promise of fast text generation due to their inherent self-correction ability compared to…

cs.LG2025

On a Connection Between Imitation Learning and RLHF

Teng Xiao, Yige Yuan, Mingxiao Li +2

This work studies the alignment of large language models with preference data from an imitation learning perspective. We establish a close theoretical connection between reinforcem…