arXiv:2609.04543v1 Announce Type: new Abstract: A key challenge in reliable LLM deployment is recognizing when uncertainty reflects irreducible…
Category: AI
Towards a universal language of concepts: A survey
arXiv:2609.04528v1 Announce Type: new Abstract: Humans can learn and generalize novel concepts from sparse data because they express knowledge in rich…
Rethinking Indirect Prompt Injection as a Test-Time Search Problem
arXiv:2609.04495v1 Announce Type: new Abstract: We formulate indirect prompt injection as a test-time search over a task-dependent attack surface induced…
What Does Multi-Harness RL Learn? Credit Assignment and Portability in Coding Agents
arXiv:2609.04518v1 Announce Type: new Abstract: Agent reinforcement learning (RL) increasingly runs through full execution harnesses, and a multi-harness…
When Quantization Breaks Memory: Recurrent-State Write-Back in Low-Precision Temporal Inference
arXiv:2609.04490v1 Announce Type: new Abstract: Quantization is widely used to reduce the computational and memory demands of neural-network inference. In…
BioSync: Transformer-Based Cross-Modal Fusion for a Multimodal Physiological Digital Biomarker
arXiv:2609.04504v1 Announce Type: new Abstract: Cardiac, neural, behavioral, and speech measurements from wearable and mobile devices provide partial,…
IFM Releases K2 Horizon: Six Apache 2.0 Models From 0.9B to 375B
Most open model launches release one checkpoint and a benchmark table. The Institute of Foundation Models (IFM) released something wider last week. IFM is…
ResLearn-XR: Residual Learning for Network Traffic and Quality-of-Experience-Aware Modeling in Extended Reality
arXiv:2609.04493v1 Announce Type: new Abstract: We present ResLearn-XR, a residual learning framework for predicting eXtended Reality (XR) network traffic…
A Removal Based Approach to Improve LLM Faithfulness at Test-Time
arXiv:2609.04343v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for consequential decisions, making their explanations…
Corporate Language Model (CLM): Transforming Tacit and Fragmented Enterprise Knowledge into a Sovereign, Auditable, and Executable Corporate Intelligence Layer
arXiv:2609.04377v1 Announce Type: new Abstract: Enterprise AI deployments fail not from model inadequacy, but because organizations lack a structured…