Skip To Main Content
Saurabh Jha on Muck Rack

Saurabh Jha

As seen in: MSN, Forbes, Nature, The Economic Times, Wiley Online Library, Psychology Today, Chicago Tribune, MDPI, Quartz, SAGE Publishing and
Radiologist interested in stories & algorithms
Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work. Claim your profile

Get in touch with Saurabh

Contact Saurabh, search articles and posts on X, monitor coverage, and track replies from one place.

Learn more about Muck Rack

Actions

Share this page

Is this you?

As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile

Articles

CADENCE: Closing the Reasoning Gap via Coverage-Adaptive On-Policy Distillation

|
By Satyam Kumar, Saurabh Jha
| huggingface.co
Get this paper in your agent: hf papers read 2607.16955 Don't have the latest CLI? curl -LsSf https://hf.co/cli/install.sh | bash Models citing this paper 0 No model linking this paper Cite arxiv.org/abs/2607.16955 in a model README.md to link it from this page. Datasets citing this paper 0 No dataset linking this paper Cite arxiv.org/abs/2607.16955 in a dataset README.md to link it from this page.
Open in Who Shared View Duplicates (9) Issue with article?

Computer Science > Cryptography and Security

|
By Saurabh Jha
| arXiv
AI safety has a missing layer. Interpretability, formal methods, security engineering, evaluation methodology, and reinforcement-learning safety each produce substantial work, but the resulting artifacts do not compose into deployable oversight: every team fielding an agentic system builds its own audit schema, policy dialect, monitoring stack, and escalation path, mostly reinventions of patterns understood elsewhere.
Open in Who Shared Issue with article?

Computer Science > Machine Learning

|
By Saurabh Jha
| arXiv
On-policy knowledge distillation transfers reasoning from large teachers to compact students, but existing approaches suffer three compounding failure modes: (i) cold-start collapse, where a fresh student assigns near-zero mass to teacher-preferred tokens; (ii) state-agnostic divergence scheduling, where time-only forward/reverse-KL interpolation ignores the student's coverage state; and (iii) binary reward sparsity, where pass/fail signals discard information from partially correct traces.
Open in Who Shared Issue with article?
See all 285 licensed articles (298 Total)