Call Context
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
From Context to Skills: Can Language Models Learn from Context Skillfully?
arXiv:2604.27660v3 Announce Type: replace Abstract: Many real-world tasks require language models (LMs) to reason over complex contexts that exceed their parametric knowledge. This calls for context learning, where LMs directly learn relevant knowledge from the given context. An intuitive solution is inference-time skill augmentation: extracting the rules and procedures from context into natural-language skills.
Context Rot in AI-Assisted Software Development: Repurposing Documentation Consistency for AI Configuration Artifacts
arXiv:2606.09090v1 Announce Type: new Abstract: Developers increasingly provide AI coding assistants with persistent context through configuration files such as CLAUDE.md, AGENTS.md, and .cursorrules. These files describe code elements, architecture, and development conventions, forming the context that guides AI tool behavior across sessions. As software evolves, this context can become stale, a phenomenon we call context rot.
Whole-Pool Setwise Reranking with Long-Context Language Models
Announce Type: new Abstract: Previous LLM-based passage re-rankers are often expensive and slow because the input context constraints require the LLM to make many dependent model calls. We study how recent long-context LLMs change this problem: when the full set of retrieved candidate passages can be shown to the model at once, ranking no longer has to be reconstructed from many overlapping local comparisons.
A Direct Approach for Handling Contextual Bandits with Latent State Dynamics
Announce Type: replace Abstract: We consider a linear contextual bandit model where contexts and rewards are governed by a finite hidden Markov chain. We first revisit the simplified model by Nelson et al. (2022), in which rewards are linear functions of the posterior probabilities over the hidden states given the observed contexts (called beliefs), rather than functions of the hidden states themselves.
A 65-nm Privacy-Preserving Neuromorphic Encoder With 7.13-nJ Efficiency, 2.38-Mb/mm^2 Item-Memory Density, and Federated Learning Support
arXiv:2606.09460v1 Announce Type: new Abstract: The increasing demand for privacy-preserving personal data analytics in smart assistants, wearable health monitors, and context-aware systems calls for hardware that is both energy-efficient and secure. This work presents a 65-nm privacy-preserving neuromorphic encoder that leverages transistor-level process variation as physically unclonable entropy for hyperdimensional computing. The proposed 2T-2T entropy cell enables compact,...
VATS: Exploiting Implicit Authority in Error-Path Injection via Systematic Mutation
arXiv:2606.07992v1 Announce Type: new Abstract: As the Model Context Protocol (MCP) standardizes tool-calling for autonomous agents, it introduces a critical, unexamined attack surface: the error-handling loop. We hypothesize that tool error messages possess implicit authority, triggering corrective reasoning modes that bypass standard safety heuristics.
Learning-to-Defer with Expert-Conditional Advice
arXiv:2603.14324v5 Announce Type: replace-cross Abstract: Learning-to-Defer routes each input to the expert that minimizes expected cost, but it assumes that the information available to every expert is fixed at decision time. Many modern systems violate this assumption: after selecting an expert, one may also choose what additional information that expert should receive, such as retrieved documents, tool outputs, or escalation context. We study this problem and call it Learning-to-Defer...
Still: Amortized KV Cache Compaction in a Single Forward Pass
Announce Type: new Abstract: The KV cache is the memory bottleneck of long-horizon language model deployment. Practically, a deployable compactor must be lightweight enough to call during inference, expressive enough to preserve context under constraint, and reusable across a trajectory. Existing compaction methods satisfy only part of this requirement: selection methods are lightweight but subset-bound, while synthesis methods are expressive but rely on per-context optimization.
Ranked MSO-enumeration over compressed words
arXiv:2606.03947v1 Announce Type: new Abstract: It is shown that the ranked query enumeration problem for a fixed MSO-query on strings can be solved with linear preprocessing and constant delay in the grammar-compressed setting, where the input string is given by a so-called straight-line program, i.e., a context-free grammar that produces exactly one string. Moreover, `ranked' means that the output tuples of the MSO-query are printed in a specific order that has to be MSO-definable. This is...
Apple is adding Apple Intelligence across its default apps
Apple is adding Apple Intelligence across its default apps Apple Intelligence can customize Safari, update your passwords, and more. Apple is integrating Apple Intelligence even deeper into its operating system's default apps. Now, besides its ability to generate and edit text, Apple announced that its suite of AI tools will enable new features in Safari, the Passwords app, Messages and more.