Channels - Task Vector Geometry Underlies Dual Modes of Task Inference in Transformers :: FRELIP Discovery

Similar Items: Task Vector Geometry Underlies Dual Modes of Task Inference in Transformers

Quick Look
Reasoning over Object Descriptions Improves Coreference Resolution in Task-Based Dialogue Systems
Quick Look
SemEval-2026 Task 7: Everyday Knowledge Across Diverse Languages and Cultures
Quick Look
mdok-style at SemEval-2026 Task 10: Finetuning LLMs for Conspiracy Detection
Quick Look
mdok-style at SemEval-2026 Task 9: Finetuning LLMs for Multilingual Polarization Detection
Quick Look
UFAL-CUNI at SemEval-2026 Task 11: An Efficient Modular Neuro-symbolic Method for Syllogistic Reasoning
Quick Look
Geometry-Calibrated Conformal Abstention for Language Models
Quick Look
DPN-LE: Dual Personality Neuron Localization and Editing for Large Language Models
Quick Look
Revisiting Semantic Role Labeling: Efficient Structured Inference with Dependency-Informed Analysis
Quick Look
Litespark Inference on Consumer CPUs: Custom SIMD Kernels for Ternary Neural Networks
Quick Look
Characterizing the Expressivity of Local Attention in Transformers
Quick Look
CA-SQL: Complexity-Aware Inference Time Reasoning for Text-to-SQL via Exploration and Compute Budget Allocation
Quick Look
Feature-Augmented Transformers for Robust AI-Text Detection Across Domains and Generators
Quick Look
Is Textual Similarity Invariant under Machine Translation? Evidence Based on the Political Manifesto Corpus
Quick Look
SC-Taxo: Hierarchical Taxonomy Generation under Semantic Consistency Constraints using Large Language Models
Quick Look
Multi-Level Narrative Evaluation Outperforms Lexical Features for Mental Health
Quick Look
From Unstructured Recall to Schema-Grounded Memory: Reliable AI Memory via Iterative, Schema-Aware Extraction
Quick Look
MM-StanceDet: Retrieval-Augmented Multi-modal Multi-agent Stance Detection
Quick Look
Can AI Be a Good Peer Reviewer? A Survey of Peer Review Process, Evaluation, and the Future
Quick Look
Beyond Semantics: Measuring Fine-Grained Emotion Preservation in Small Language Model-Based Machine Translation
Quick Look
Ease of dependency distance minimization in star-like structures
Quick Look
Models Recall What They Violate: Constraint Adherence in Multi-Turn LLM Ideation
Quick Look
Universal statistical laws governing culinary design
Quick Look
Latent-GRPO: Group Relative Policy Optimization for Latent Reasoning
Quick Look
Repetition over Diversity: High-Signal Data Filtering for Sample-Efficient German Language Modeling