LinguaLift

university

AI & ML interests

None defined yet.

Recent Activity

amanchadha submitted a paper 37 minutes ago

Weights or Skills? A Survey of Robot-Learning Techniques: from Action-Predicting Weights to Robots that Write their Own Skills

amanchadha submitted a paper about 1 hour ago

FactorJEPA: Factorizing Monolithic Futures into Layout-Agent-Interaction Channels for Crowded and Chaotic Global South Urban Worlds

amanchadha authored a paper 10 days ago

Khondo: A Multimodal Benchmark for Document Packet Splitting of Bangla Forms

View all activity

submitted a paper to Daily Papers 37 minutes ago

Weights or Skills? A Survey of Robot-Learning Techniques: from Action-Predicting Weights to Robots that Write their Own Skills

Paper • 2608.01851 • Published 5 days ago

submitted a paper to Daily Papers about 1 hour ago

FactorJEPA: Factorizing Monolithic Futures into Layout-Agent-Interaction Channels for Crowded and Chaotic Global South Urban Worlds

Paper • 2608.01049 • Published 6 days ago

authored a paper 10 days ago

Khondo: A Multimodal Benchmark for Document Packet Splitting of Bangla Forms

Paper • 2607.21780 • Published 16 days ago

authored a paper 13 days ago

BaFCo: A Document Understanding Benchmark for Complex Bangla Form Comprehension

Paper • 2607.05614 • Published Jul 6

authored 2 papers 2 months ago

MAAT: Multi-phase Adapter-Aware Targeted Unlearning

Paper • 2605.30514 • Published May 28 • 7

TAPIOCA: Why Task- Aware Pruning Improves OOD model Capability

Paper • 2605.14738 • Published May 20

submitted a paper to Daily Papers 2 months ago

MAAT: Multi-phase Adapter-Aware Targeted Unlearning

Paper • 2605.30514 • Published May 28 • 7

authored a paper 2 months ago

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

Paper • 2605.18856 • Published May 13

authored a paper 3 months ago

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

Paper • 2605.10376 • Published May 11 • 2

submitted a paper to Daily Papers 3 months ago

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

Paper • 2605.10376 • Published May 11 • 2

authored a paper 3 months 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 3 months ago

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

Paper • 2605.09169 • Published May 9

authored 4 papers 3 months 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 3 months 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 4 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 4 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 5 months ago

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

Paper • 2603.21854 • Published Mar 23 • 3