· ai
[Paper] Sigmoid Head for Quality Estimation under Language Ambiguity
Language model (LM) probability is not a reliable quality estimator, as natural language is ambiguous. When multiple output options are valid, the model's proba...
-
- · ai
[Paper] QSLM: A Performance- and Memory-aware Quantization Framework with Tiered Search Strategy for Spike-driven Language Models
Large Language Models (LLMs) have been emerging as prominent AI models for solving many natural language tasks due to their high performance (e.g., accuracy) an...
- · ai
[Paper] IRPO: Scaling the Bradley-Terry Model via Reinforcement Learning
Generative Reward Models (GRMs) have attracted considerable research interest in reward modeling due to their interpretability, inference-time scalability, and ...
- · ai
[Paper] Fast-weight Product Key Memory
Sequence modeling layers in modern language models typically face a trade-off between storage capacity and computational efficiency. While Softmax attention off...
- · ai
[Paper] Three factor delay learning rules for spiking neural networks
Spiking Neural Networks (SNNs) are dynamical systems that operate on spatiotemporal data, yet their learnable parameters are often limited to synaptic weights, ...
- · ai
[Paper] Physio-DPO: Aligning Large Language Models with the Protein Energy Landscape to Eliminate Structural Hallucinations
Large Protein Language Models have shown strong potential for generative protein design, yet they frequently produce structural hallucinations, generating seque...
- · devops
[Paper] FlexSpec: Frozen Drafts Meet Evolving Targets in Edge-Cloud Collaborative LLM Speculative Decoding
Deploying large language models (LLMs) in mobile and edge computing environments is constrained by limited on-device resources, scarce wireless bandwidth, and f...
- · ai
[Paper] Probabilistic Guarantees for Reducing Contextual Hallucinations in LLMs
Large language models (LLMs) frequently produce contextual hallucinations, where generated content contradicts or ignores information explicitly stated in the p...
- · software
[Paper] SEMODS: A Validated Dataset of Open-Source Software Engineering Models
Integrating Artificial Intelligence into Software Engineering (SE) requires having a curated collection of models suited to SE tasks. With millions of models ho...
- · software
[Paper] KELP: Robust Online Log Parsing Through Evolutionary Grouping Trees
Real-time log analysis is the cornerstone of observability for modern infrastructure. However, existing online parsers are architecturally unsuited for the dyna...
- · software
[Paper] Towards Understanding and Characterizing Vulnerabilities in Intelligent Connected Vehicles through Real-World Exploits
Intelligent Connected Vehicles (ICVs) are a core component of modern transportation systems, and their security is crucial as it directly relates to user safety...
- · ai
[Paper] Beyond IVR: Benchmarking Customer Support LLM Agents for Business-Adherence
Traditional customer support systems, such as Interactive Voice Response (IVR), rely on rigid scripts and lack the flexibility required for handling complex, po...