LinguaLift

university

AI & ML interests

None defined yet.

Recent Activity

amanchadha authored a paper 9 days ago

MAAT: Multi-phase Adapter-Aware Targeted Unlearning

amanchadha authored a paper 9 days ago

TAPIOCA: Why Task- Aware Pruning Improves OOD model Capability

amanchadha submitted a paper 9 days ago

MAAT: Multi-phase Adapter-Aware Targeted Unlearning

View all activity

authored 2 papers 9 days ago

MAAT: Multi-phase Adapter-Aware Targeted Unlearning

Paper • 2605.30514 • Published 13 days ago • 7

TAPIOCA: Why Task- Aware Pruning Improves OOD model Capability

Paper • 2605.14738 • Published 21 days ago

submitted a paper to Daily Papers 9 days ago

MAAT: Multi-phase Adapter-Aware Targeted Unlearning

Paper • 2605.30514 • Published 13 days ago • 7

authored a paper 16 days ago

SPHERICAL KV: Angle-Domain Attention and Rate-Distortion Retention for Efficient Long-Context Inference

Paper • 2605.18856 • Published 28 days ago

authored a paper 27 days ago

SleepWalk: A Three-Tier Benchmark for Stress-Testing Instruction-Guided Vision-Language Navigation

Paper • 2605.10376 • Published about 1 month ago • 2

submitted a paper to Daily Papers 27 days ago

SleepWalk: A Three-Tier Benchmark for Stress-Testing Instruction-Guided Vision-Language Navigation

Paper • 2605.10376 • Published about 1 month ago • 2

authored a paper 28 days ago

Prediction Bottlenecks Don't Discover Causal Structure (But Here's What They Actually Do)

Paper • 2605.09169 • Published May 9

submitted a paper to Daily Papers 28 days ago

Prediction Bottlenecks Don't Discover Causal Structure (But Here's What They Actually Do)

Paper • 2605.09169 • Published May 9

authored 4 papers about 1 month ago

Moral Sensitivity in LLMs: A Tiered Evaluation of Contextual Bias via Behavioral Profiling and Mechanistic Interpretability

Paper • 2605.03217 • Published May 4 • 1

VISTA: Video Interaction Spatio-Temporal Analysis Benchmark

Paper • 2605.01391 • Published May 2

PermaFrost-Attack: Stealth Pretraining Seeding(SPS) for planting Logic Landmines During LLM Training

Paper • 2604.22117 • Published Apr 28

Personality Shapes Gender Bias in Persona-Conditioned LLM Narratives Across English and Hindi: An Empirical Investigation

Paper • 2604.23600 • Published Apr 26 • 2

submitted a paper to Daily Papers about 1 month ago

Personality Shapes Gender Bias in Persona-Conditioned LLM Narratives Across English and Hindi: An Empirical Investigation

Paper • 2604.23600 • Published Apr 26 • 2

authored a paper about 2 months ago

CONSCIENTIA: Can LLM Agents Learn to Strategize? Emergent Deception and Trust in a Multi-Agent NYC Simulation

Paper • 2604.09746 • Published Apr 10 • 1

submitted a paper to Daily Papers about 2 months ago

CONSCIENTIA: Can LLM Agents Learn to Strategize? Emergent Deception and Trust in a Multi-Agent NYC Simulation

Paper • 2604.09746 • Published Apr 10 • 1

authored a paper 3 months ago

Reasoning or Rhetoric? An Empirical Analysis of Moral Reasoning Explanations in Large Language Models

Paper • 2603.21854 • Published Mar 23 • 3

submitted a paper to Daily Papers 3 months ago

Reasoning or Rhetoric? An Empirical Analysis of Moral Reasoning Explanations in Large Language Models

Paper • 2603.21854 • Published Mar 23 • 3

authored 2 papers 3 months ago

SAHOO: Safeguarded Alignment for High-Order Optimization Objectives in Recursive Self-Improvement

Paper • 2603.06333 • Published Mar 6 • 1

The Reasoning Trap -- Logical Reasoning as a Mechanistic Pathway to Situational Awareness

Paper • 2603.09200 • Published Mar 10 • 5

submitted a paper to Daily Papers 3 months ago

The Reasoning Trap -- Logical Reasoning as a Mechanistic Pathway to Situational Awareness

Paper • 2603.09200 • Published Mar 10 • 5