Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Vinay Kumar

Vinay Kumar

7 indexed papers

Recent (6 mo)
7
With code
0
Influential cites
0
Benchmarked
0

Publications per year

7
26

Top categories

AI×5ML×4NLP×3Vision×3Info Retrieval×1Software Eng.×1Quantum Physics×1Networking×1

Frequent co-authors

Vinay Kumar Sankarapu3×
Pratinav Seth3×
Vinay Kumar Verma3×
Mohammed Asad Karim2×
Shreeyans Arora1×
Utsav Avaiya1×

Research Timeline

2026
FOCUS: Forcing In-Context Object Localization through Visual Support Constraints and Policy Optimization

The paper introduces a novel two-stage framework to achieve robust, category-agnostic object localization in-context (ICL) by optimizing attention and minimizing localization error using reinforcement learning.

FOCUS: Forcing In-Context Object Localization through Visual Support Constraints and Policy Optimization

The paper introduces a novel two-stage framework to achieve robust, category-agnostic object localization in-context (ICL) by optimizing attention and minimizing localization error using reinforcement learning.

Provenance-Grounded Gating and Adaptive Recovery in Synthetic Post-Training Data Curation

This paper investigates the effectiveness of filtering and recovery methods in synthetic post-training pipelines.

ALIGNBEAM : Inference-Time Alignment Transfer via Cross-Vocabulary Logit Mixing

The paper presents ALIGNBEAM, a training-free method to improve the safety of large language models by translating anchor logits into the target model's vocabulary and selecting the safest continuation.

Making Quantum Networks Work: Routing, Calibration, and Programmable Quantum Repeaters

This paper studies the architecture, routing, and operation of quantum networks under realistic constraints.

Source-Free Controlled Adaptation of Teachers for Continual Test-Time Adaptation

This paper proposes a source-free continual test-time adaptation methodology using a controlled teacher adaptation and class prototype estimation.

AuditKIT: A Unified Evaluation Spine for Benchmarking, Judging, and Comparing Large Language Models and Agentic Systems

The paper presents AuditKIT, a library for evaluating language models and agents by recording various measurements in one result representation.

Highlighted terms show continued research focus across papers

Papers

cs.CLcs.AIcs.IREmpiricalRecentOct 15, 2026

AuditKIT: A Unified Evaluation Spine for Benchmarking, Judging, and Comparing Large Language Models and Agentic Systems

Shreeyans Arora, Utsav Avaiya, Zera Lyngkhoi, Hem Gosalia +3 more

The paper presents AuditKIT, a library for evaluating language models and agents by recording various measurements in one result representation.

View →
cs.LGcs.CVEmpirical
Recent
Jul 26, 2026

Source-Free Controlled Adaptation of Teachers for Continual Test-Time Adaptation

Anurag Roy, Riddhiman Moulick, Vinay Kumar Verma, Saptarshi Ghosh +1 more

This paper proposes a source-free continual test-time adaptation methodology using a controlled teacher adaptation and class prototype estimation.

View →
quant-phcs.NIEmpiricalRecentJun 21, 2026

Making Quantum Networks Work: Routing, Calibration, and Programmable Quantum Repeaters

Vinay Kumar

This paper studies the architecture, routing, and operation of quantum networks under realistic constraints.

View →
cs.CLcs.AIcs.ETEmpiricalRecentJun 10, 2026

ALIGNBEAM : Inference-Time Alignment Transfer via Cross-Vocabulary Logit Mixing

Chirag Chawla, Pratinav Seth, Vinay Kumar Sankarapu

The paper presents ALIGNBEAM, a training-free method to improve the safety of large language models by translating anchor logits into the target model's vocabulary and selecting the safest continuatio…

View →
cs.CLcs.AIEmpiricalRecentJun 9, 2026

Provenance-Grounded Gating and Adaptive Recovery in Synthetic Post-Training Data Curation

Soham Bhattacharjee, Karun Sharma, Vinay Kumar Sankarapu, Pratinav Seth

This paper investigates the effectiveness of filtering and recovery methods in synthetic post-training pipelines.

View →
cs.CVcs.AIcs.LGRecentMay 29, 2026

FOCUS: Forcing In-Context Object Localization through Visual Support Constraints and Policy Optimization

Mohammed Asad Karim, Vinay Kumar Verma

The paper introduces a novel two-stage framework to achieve robust, category-agnostic object localization in-context (ICL) by optimizing attention and minimizing localization error using reinforcement…

View →
cs.CVcs.AIcs.LGRecentMay 29, 2026

FOCUS: Forcing In-Context Object Localization through Visual Support Constraints and Policy Optimization

Mohammed Asad Karim, Vinay Kumar Verma

The paper introduces a novel two-stage framework to achieve robust, category-agnostic object localization in-context (ICL) by optimizing attention and minimizing localization error using reinforcement…

View →