AI Wiki — Knowledge Base

GeoContext: One Context Ladder, Two Failure Modes in Vision-Language Geolocation: Flat Reliance on User-Provided Location Context and False Confirmation of Location Claims

arXiv:2609.05761v1 Announce Type: new Abstract: Visual geolocation benchmarks typically ask a model where an image was captured without accounting for the location context that users often provide. We

model-releasesarxiv-cs-cv

9 Sept 2026

Search: “context”

Closing the Context Gap: Activation Alignment for Tabular In-Context Learning

Compile, Don't Memorize: A Context Compilation Architecture (CCA) for In-Context Learning

Contexting as Recommendation: Evolutionary Collaborative Filtering for Context Engineering

Dense Contexts Are Hard Contexts: Lexical Density Limits Effective Context in LLMs

Context Is What You Need: The Maximum Effective Context Window for Real World Limits of LLMs

Contrast Matters: Understanding Robustness of In-Context Fine-Tuning to Target-Context Relatedness

No-Worse Context-Aware Decoding: Preventing Neutral Regression in Context-Conditioned Generation

Load-Bearing Context: The Question Damage Score for Evaluating Context Reliance in Linguistic Reasoning

OctoLong: Mid-Training On Cross-Repository Code Contexts Enhances Long-Context Modeling

Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context

ContextPilot: Fast Long-Context Inference via Context Reuse

Shuffle the Context: RoPE-Perturbed Self-Distillation for Long-Context Adaptation

UT-ACA: Uncertainty-Triggered Adaptive Context Allocation for Long-Context Inference

LLM Agents Are Latent Context Managers: Eliciting Self-Managed Context via a Proprioceptive Dashboard

PEEK: Context Map as an Orientation Cache for Long-Context LLM Agents

From Context to Skills: Can Language Models Learn from Context Skillfully?

Mixed-Initiative Context: Structuring and Managing Context for Human-AI Collaboration

Residual Vector-based Reconstruction as Long-Context Recall Regardless of Context Window Size

Longer Context, Deeper Thinking: Uncovering the Role of Long-Context Ability in Reasoning

Evaluation Framework for Highlight Explanations of Context Utilisation in Language Models

When Context Sticks: Studying Interference in In-Context Learning

SHINE: A Scalable In-Context Hypernetwork for Mapping Context to LoRA in a Single Pass

Emergent Misalignment via In-Context Learning: Narrow in-context examples can produce broadly misaligned LLMs

Beyond the Context Window: An Adaptive Entropy-Based Routing Framework for Hybrid Retrieval and Long-Context Language Models

ACM: Agentic Context Management for Long Horizon Tasks

100-LongBench: Are de facto Long-Context Benchmarks Literally Evaluating Long-Context Ability?

When Context Misleads: In-context Learning with Jurisdiction in Large Language Models

LoGIC: Budgeted Context Construction for Node-Level Graph In-Context Learning with Tabular Foundation Models

When Context Returns: Toward Robust Internalization in On-Policy Distillation

Chunks as Arms: Multi-Armed Bandit-Guided Sampling for Long-Context LLM Preference Optimization

Rethinking Faithfulness in LLMs: A Pairwise Context-Sensitive Perspective

Considering Context: When World Models Need Context Encoders

Multi-Context Fusion Transformer for Pedestrian Crossing Intention Prediction in Urban Environments

Distractor-Aware Truncation: Disentangling Context-Length Effects from Signal Loss in Long-Context LLM Benchmarks

Sequential Correlations Change In-Context Learning: Effective Context Length and Architectural Mismatch

LongAttnComp: Cross-Family Context Compression for Long-Context Reasoning

Compress the Context, Keep the Commitments: A Formal Framework for Verifiable LLM Context Compression

LIFT: A Novel Framework for Enhancing Long-Context Understanding of LLMs via Long Input Fine-Tuning

RecaLLM: Addressing the Lost-in-Thought Phenomenon with Explicit In-Context Retrieval

When Agent Context Goes Stale: Incoherence in Volatile Agent Context

Downstream-Aware Context Selection for Online In-Context Reinforcement Learning

GeoContext: One Context Ladder, Two Failure Modes in Vision-Language Geolocation: Flat Reliance on User-Provided Location Context and False Confirmation of Location Claims

PERK: Long-Context Reasoning as Test-Time Learning

In-Context Forcing: Uncovering Context Effects in Autoregressive Video Diffusion

Where Does Long-Context Supervision Actually Go? Effective-Context Exposure Balancing

OPSDL: On-Policy Self-Distillation for Long-Context Language Models

DySCO: Dynamic Attention-Scaling Decoding for Long-Context Language Models

TAFFY: A Task-Adaptive Tabular Foundation Model with In-Context Diversity