arXiv AI
Aug 13
RealisticTritonBench: A Benchmark for Triton-Kernel Generation in Real-World AI Frameworks
arXiv:2608. 12004v1 Announce Type: cross Abstract: In modern AI frameworks, GPU kernels are key to overall system performance.
Benchmarks and evaluation
Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv AI
Aug 13
Localizing Safety Alignment: MLP Layers and Mid-Network Blocks Encode Refusal Behavior in Large Language Models
arXiv:2608. 11583v1 Announce Type: new Abstract: Safety alignment in large language models is often treated as a distributed property of the entire network, yet its practical brittleness suggests that refusal behavior may be concentrated in a smaller set of parameters.
arXiv AI
Aug 13
DexterSQL: Deep Schema Exploration and Rule-based Correction for Text-to-SQL Generation
arXiv:2608. 11889v1 Announce Type: cross Abstract: Prompting-based (\textit{i}.
arXiv AI
Aug 13
AI4AI at Test-Time: Strong-to-Weak Capability Transfer via Harnesses
arXiv:2608. 12307v1 Announce Type: cross Abstract: Recent work on distillation transfers the capabilities of large models to smaller ones often by updating the latter's parameters, through teacher forcing, on-policy distillation, and related training-time methods.
arXiv AI
Aug 13
Tools as Continuous Flow for Evolving Agentic Reasoning
arXiv:2605. 07339v2 Announce Type: replace Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities in orchestrating tools for reasoning tasks.
arXiv AI
Aug 13
Behavior and Representation in Open-Weight Large Language Models for Combinatorial Optimization: From Feature Extraction to Algorithm Selection
arXiv:2512. 13374v2 Announce Type: replace Abstract: Recent advances in Large Language Models (LLMs) open new perspectives for automation in optimization, yet little is known about whether their internal representations capture problem structure or algorithmic behavior.
arXiv AI
Aug 13
NetlistBench: Evaluating LLM Reliability in SPICE Netlist Recognition and Manipulation
arXiv:2608. 12197v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used in circuit design workflows, yet their reliability on simulator-facing SPICE netlist recognition and manipulation remains poorly understood and is rarely separated from high-level design reasoning.
arXiv AI
Aug 13
Program Semantic Inequivalence Game with Large Language Models
arXiv:2505. 03818v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) can achieve strong performance on everyday coding tasks, but they can fail on complex tasks that require non-trivial reasoning about program semantics.
arXiv AI
Aug 13
Representation Finetuning for Continual Learning
arXiv:2603. 11201v3 Announce Type: replace-cross Abstract: The world is inherently dynamic, and continual learning aims to enable models to adapt to ever-evolving data streams.
arXiv Machine Learning
Aug 13
When Offline Evaluation Misleads: A Diagnostic Protocol for Reward and Policy Selection in Delayed-Feedback Contextual Bandits
arXiv:2608. 11560v1 Announce Type: new Abstract: Personalizing marketing messages with contextual multi-armed bandits (CMABs) drives real business value, yet the objective that ultimately matters - a downstream conversion - is observed only weeks later, too late to drive online learning.
arXiv Machine Learning
Aug 13
Mechanism Design for Generative Engines: From Exploitation toward Win-Win Outcomes
arXiv:2608. 11390v1 Announce Type: new Abstract: Generative engines are reshaping the web ecosystem by making citations a key mechanism for allocating attention, attribution, and downstream value.
arXiv Machine Learning
Aug 13
Generative Learning for Quantum Measurement Design
arXiv:2608. 11396v1 Announce Type: cross Abstract: Extracting quantum information from a quantum state is a fundamental task of quantum computation, often requiring the estimation of many non-commuting observables under a finite measurement budget.
arXiv Machine Learning
Aug 13
Large-scale AI-Ready Data for Anti-Cancer Drug Response Modeling
arXiv:2608. 11444v1 Announce Type: cross Abstract: Drug response prediction (DRP) models are an active area of research in pharmacogenomics, with growing potential to accelerate the identification of effective anticancer drugs.
arXiv Machine Learning
Aug 13
Reliable Inference in Edge-Cloud Model Cascades via Conformal Alignment
arXiv:2510. 17543v3 Announce Type: replace Abstract: Edge intelligence enables low-latency inference via compact on-device models, but assuring reliability remains challenging.
arXiv AI
Aug 13
TRACE Bench: Task-driven Roleplay Agentic Checklist Evaluation
arXiv:2608. 11236v1 Announce Type: cross Abstract: Roleplay evaluation should do more than assign a single score: it should reveal which role requirements were tested, which failed, and which dialogue evidence supports the judgment.
arXiv AI
Aug 13
Teaching agentic AI to learn expert reasoning for rare disease diagnosis
arXiv:2606. 16149v3 Announce Type: replace Abstract: Rare disease diagnosis depends on expert reasoning that is scarce and difficult to transfer; off-the-shelf large language models (LLMs) rank the correct disease first in only 35.
arXiv AI
Aug 13
Locating and Controlling Implicit Personalization in Large Language Models
arXiv:2608. 11735v1 Announce Type: cross Abstract: Large language models (LLMs) often shift their outputs in response to implicit demographic cues even when users never state a demographic identity.
arXiv AI
Aug 13
From Synthesis to Removal: Physics-Grounded Reflection Simulation and Diffusion-Based Video Dereflection
arXiv:2608. 11562v1 Announce Type: cross Abstract: Videos captured through glass often contain reflections that degrade visual quality and interfere with downstream vision tasks.
arXiv AI
Aug 13
Diffuse to Compress: Leveraging Diffusion LMs for Lossless Compression
arXiv:2608. 11249v1 Announce Type: cross Abstract: We study the problem of lossless text compression, motivated by the rapid growth in the collection and storage of digital textual data - including plain text, source code, and structured formats such as XML - and by recent advances in neural language model-based compression.
arXiv AI
Aug 13
EnterpriseRAG: Benchmarking LLM Instruction Adherence and Robustness under Non-Ideal Enterprise Retrieval
arXiv:2608. 11584v1 Announce Type: new Abstract: Enterprise RAG deployments face a critical reliability gap: while LLMs satisfy 80% of individual constraints, only 26.