Avi

avahal's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

commented 7 papers about 15 hours ago

EvolVE: Evolutionary Search for LLM-based Verilog Generation and Optimization

Paper • 2601.18067 • Published 3 days ago • 1 •

3

Benchmarks Saturate When The Model Gets Smarter Than The Judge

Paper • 2601.19532 • Published 2 days ago • 1 •

3

GPCR-Filter: a deep learning framework for efficient and precise GPCR modulator discovery

Paper • 2601.19149 • Published 2 days ago • 1 •

4

HalluCitation Matters: Revealing the Impact of Hallucinated References with 300 Hallucinated Papers in ACL Conferences

Paper • 2601.18724 • Published 3 days ago • 4 •

2

Revisiting Parameter Server in LLM Post-Training

Paper • 2601.19362 • Published 2 days ago • 5 •

3

Selective Steering: Norm-Preserving Control Through Discriminative Layer Selection

Paper • 2601.19375 • Published 2 days ago • 5 •

3

Post-LayerNorm Is Back: Stable, ExpressivE, and Deep

Paper • 2601.19895 • Published 1 day ago • 11 •

3

commented 8 papers about 16 hours ago

FABLE: Forest-Based Adaptive Bi-Path LLM-Enhanced Retrieval for Multi-Document Reasoning

Paper • 2601.18116 • Published 3 days ago • 11 •

3

TriPlay-RL: Tri-Role Self-Play Reinforcement Learning for LLM Safety Alignment

Paper • 2601.18292 • Published 3 days ago • 9 •

3

AVMeme Exam: A Multimodal Multilingual Multicultural Benchmark for LLMs' Contextual and Cultural Knowledge and Thinking

Paper • 2601.17645 • Published 4 days ago • 21 •

3

World Craft: Agentic Framework to Create Visualizable Worlds via Text

Paper • 2601.09150 • Published 15 days ago • 15 •

3

Visual Generation Unlocks Human-Like Reasoning through Multimodal World Models

Paper • 2601.19834 • Published 1 day ago • 19 •

4

A Pragmatic VLA Foundation Model

Paper • 2601.18692 • Published 3 days ago • 34 •

4

AdaReasoner: Dynamic Tool Orchestration for Iterative Visual Reasoning

Paper • 2601.18631 • Published 3 days ago • 44 •

4

AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security

Paper • 2601.18491 • Published 3 days ago • 83 •

7

commented 5 papers 1 day ago

Guidelines to Prompt Large Language Models for Code Generation: An Empirical Characterization

Paper • 2601.13118 • Published 10 days ago • 2 •

3

VISTA-PATH: An interactive foundation model for pathology image segmentation and quantitative analysis in computational pathology

Paper • 2601.16451 • Published 6 days ago • 2 •

3

Knowledge is Not Enough: Injecting RL Skills for Continual Adaptation

Paper • 2601.11258 • Published 13 days ago • 5 •

3

ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch

Paper • 2601.13606 • Published 9 days ago • 6 •

3

Mecellem Models: Turkish Models Trained from Scratch and Continually Pre-trained for the Legal Domain

Paper • 2601.16018 • Published 7 days ago • 7 •

4