AM

Avni Mittal

cs.CLcs.AIcs.LGcs.MAcs.GTcs.HC

On Valency

published · living versions

W_3b8zvz6v·v1 · currentpublished

VIAS: Value-Isolating Activation Steering for Multi-Value Alignment and Compliance for Organisations

with Avinash Anand, Dikshant Kukreja, Erik Cambria, Rajiv Ratn Shah +1

1 version

W_j5854z57·v1published

Sonar-MoE: In-Backward Expert Updates for Memory-Efficient Mixture-of-Experts Training

Preprints & journals

7 papers in the corpus · 2026

TextNCA: Neural Cellular Automata for Language Modeling via Hierarchical Local Attention2608.02050v1 · Avni Mittal, Avinash Anand, Ashutosh Kumar et al.2026 · 0 citationsarXiv

Triadic Werewolf: A Jester Role for Multi-Hop Theory of Mind in LLMs2606.27909v1 · Avni Mittal2026 · 0 citationsarXiv

The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes2606.11470v2 · Avinash Anand, Mahisha Ramesh, Avni Mittal et al.2026 · 0 citationsarXiv

Litmus (Re)Agent: A Benchmark and Agentic System for Predictive Evaluation of Multilingual Models2604.08970v1 · Avni Mittal, Shanu Kumar, Sandipan Dandapat et al.2026 · 0 citationsarXiv

Do LLMs Follow Their Own Rules? A Reflexive Audit of Self-Stated Safety Policies2604.09189v1 · Avni Mittal2026 · 0 citationsarXiv

Did You Forget What I Asked? Prospective Memory Failures in Large Language Models2603.23530v2 · Avni Mittal2026 · 0 citationsarXiv

C2-Faith: Benchmarking LLM Judges for Causal and Coverage Faithfulness in Chain-of-Thought Reasoning2603.05167v2 · Avni Mittal, Rauno Arike2026 · 0 citationsarXiv

Career total: 11 works. 7 are in this corpus.

Profile built from the corpus for this byline.

Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.