Samyak Jha

According to our database, Samyak Jha authored at least 5 papers between 2024 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2026

When Language Overwrites Vision: Over-Alignment and Geometric Debiasing in Vision-Language Models.

Harshvardhan Saini, Samyak Jha, Yiming Tang, Dianbo Liu

CoRR, May, 2026

CAPA: Contribution-Aware Pruning and FFN Approximation for Efficient Large Vision-Language Models.

Samyak Jha, Junho Kim

CoRR, February, 2026

CRoPS: A Training-Free Hallucination Mitigation Framework for Vision-Language Models.

Neeraj Anand, Samyak Jha, Udbhav Bamba, Rahul Rahaman

Trans. Mach. Learn. Res., 2026

2025

Langevin Monte-Carlo Provably Learns Depth Two Neural Nets at Any Size and Data.

Dibyakanti Kumar, Samyak Jha, Anirbit Mukherjee

CoRR, March, 2025

2024

Global Convergence of SGD For Logistic Loss on Two Layer Neural Nets.

Pulkit Gopalani, Samyak Jha, Anirbit Mukherjee

Trans. Mach. Learn. Res., 2024