TechniqueRLHF / Alignment8 recent entries15 Oct 2026Cross-Scenario Industrial Defect Detection via Domain-Robust Training and Metric-Aligned SelectionarXiv:2610.19540v1 Announce Type: new Abstract: Automated defect detection of industrial boards must remain highly reliable under cross-scenario variations in lighting, surface contaminants, and produ→15 Oct 2026Cross-Lingual TTS for Indian Languages: A Benchmark and Inference-Time Duration Estimation StrategiesarXiv:2610.14826v1 Announce Type: cross Abstract: Recent alignment-free Text-to-Speech (TTS) models achieve high synthesis quality by removing explicit alignment modules and simplifying training. Howe
TechniqueRAG8 recent entries15 Oct 2026LaCache: Robust Semantic Caching for LLM ServingarXiv:2608.01718v2 Announce Type: replace Abstract: Semantic caching, reusing responses to answer semantically similar queries, has seen growing adoption in LLM serving, offering faster responses and →15 Oct 2026Label-Centric Knowledge Retrieval for Zero-Shot Text ClassificationarXiv:2610.16182v1 Announce Type: new Abstract: Flagship large language models (LLMs) offer rich general knowledge and strong reasoning capabilities, but their high inference cost and latency limit th→15 Oct 2026Iterative Critique-Refine Framework for Enhancing LLM PersonalizationarXiv:2510.24469v2 Announce Type: replace-cross Abstract: Personalized text generation requires models not only to produce coherent text but also to align with a target user's style, tone, and topical→15 Oct 2026Horizon Scans can be accelerated using novel information retrieval and artificial intelligence toolsarXiv:2504.01627v2 Announce Type: replace-cross Abstract: Introduction: Horizon scanning in healthcare assesses early signals of innovation, crucial for timely adoption. Current horizon scanning faces→15 Oct 2026Have You Been Convinced? A Neuro-symbolic Argumentation Reasoning Approach to Detecting Persuasiveness in ChangeMyView DiscussionsarXiv:2610.15091v1 Announce Type: cross Abstract: Argument structures represent how individual arguments interact within a discourse. However, leveraging these structures to infer meaningful knowledge→15 Oct 2026CHEAR: Confusion-Hierarchy Evidence-Aware Reasoning for Cost-Efficient Human Activity RecognitionarXiv:2610.15298v1 Announce Type: new Abstract: Large language models (LLMs) offer a new approach to wearable-sensor-based human activity recognition. Retrieval-augmented generation (RAG) further intr→15 Oct 2026AutoSec-RAN: Specification-Grounded LLM Fine-Tuning for Automated Security Analysis of O-RANarXiv:2610.15995v1 Announce Type: cross Abstract: This paper presents AutoSec-RAN, a specification-grounded large language model (LLM) framework for automated security triage of Open Radio Access Netw→15 Oct 2026AtomSearch: Evidence-Grounded Tree Search for Agent Skill OptimizationarXiv:2610.19951v1 Announce Type: new Abstract: Agent skills adapt frozen models through editable external instructions. Revising several rules at once makes changes difficult to inspect, while judgin
TechniqueAgents8 recent entries15 Oct 2026AtomSearch: Evidence-Grounded Tree Search for Agent Skill OptimizationarXiv:2610.19951v1 Announce Type: new Abstract: Agent skills adapt frozen models through editable external instructions. Revising several rules at once makes changes difficult to inspect, while judgin→15 Oct 2026AReaL-RSI: Adaptive Scaling and Coordination of Recursive Self-ImprovementarXiv:2610.18083v1 Announce Type: new Abstract: Scaling recursive self-improvement requires additional computation to produce useful research progress in reaching persistent objectives. Intuitively, m→15 Oct 2026Anuvani-LID: Robust and Calibrated Spoken Language Identification for Indian LanguagesarXiv:2610.20263v1 Announce Type: new Abstract: Every multilingual speech pipeline begins with a language decision, an error there propagates silently through recognition, translation and routing. In →15 Oct 2026AgriJev: Efficient Agricultural Candidate Scoring with Multi-Scale Adapted ModelsarXiv:2610.19478v1 Announce Type: new Abstract: Agricultural systems make decisions over heterogeneous entity types, textual judgments, and knowledge-question options. Generating a textual answer adds→15 Oct 2026Adaptive-Group Process Rewards for GUI AgentsarXiv:2610.17710v1 Announce Type: new Abstract: Training graphical user interface (GUI) agents with reinforcement learning suffers from sparse outcome rewards, leading to inefficient learning. Process→15 Oct 2026A Reference Architecture for Integrating Agentic AI into Enterprise Software: Responsibilities, Interactions, and VariabilityarXiv:2610.14818v1 Announce Type: new Abstract: Agentic AI moves generative AI applications toward systems that coordinate reasoning, enterprise context, model inference, and external actions. Integra→15 Oct 2026A Counterfactual Graph Approach to Oppositional Narrative AnalysisarXiv:2603.06135v3 Announce Type: replace-cross Abstract: Distinguishing legitimate critical speech from coordinated conspiracy narratives is a pressing challenge for the integrity of the online infor→15 Oct 20264x R9700 builds with 127 used EPYCs: 10.7k all-in per machine. I built three (384GB VRAM)I saw the 4x R9700 build for a 10-person startup here a few days ago and wanted to share my results, since I opted to spend most of the money on the cards. I went with a super cheap used EPYC instead
TechniqueFine-tuning8 recent entries15 Oct 2026D2: High-Capability Full-Duplex Spoken Language Models from Half-Duplex BackbonesarXiv:2610.17124v1 Announce Type: cross Abstract: Full-duplex spoken language models (FD-SLMs) support simultaneous listening and speaking, but often lag behind half-duplex spoken language models (HD-→15 Oct 2026Cross-Scenario Industrial Defect Detection via Domain-Robust Training and Metric-Aligned SelectionarXiv:2610.19540v1 Announce Type: new Abstract: Automated defect detection of industrial boards must remain highly reliable under cross-scenario variations in lighting, surface contaminants, and produ→15 Oct 2026CLIVO: Differentiable Cluster-Based Instruction Mixing with Learned Validation ObjectivesarXiv:2610.16876v1 Announce Type: new Abstract: Target-aware multimodal instruction selection requires useful examples and an appropriate balance of supervision. Sample-level rankings can overrepresen→15 Oct 2026Chain of Time: In-Context Physical Simulation with Image Generation ModelsarXiv:2511.00110v2 Announce Type: replace Abstract: We propose a novel cognitively-inspired prompting method to stabilize and interpret the physical simulation produced by autoregressive image generat→15 Oct 2026Beyond Successful Play: Diagnosing Opponent Modeling in Large Language ModelsarXiv:2610.17310v1 Announce Type: new Abstract: Language-model agents are expected to adapt to others whose behavior changes through interaction. Yet adaptation may rely on learned behavioral patterns→15 Oct 2026AutoSec-RAN: Specification-Grounded LLM Fine-Tuning for Automated Security Analysis of O-RANarXiv:2610.15995v1 Announce Type: cross Abstract: This paper presents AutoSec-RAN, a specification-grounded large language model (LLM) framework for automated security triage of Open Radio Access Netw→15 Oct 2026AtomSearch: Evidence-Grounded Tree Search for Agent Skill OptimizationarXiv:2610.19951v1 Announce Type: new Abstract: Agent skills adapt frozen models through editable external instructions. Revising several rules at once makes changes difficult to inspect, while judgin→15 Oct 2026AdaptFuse: Training-Free Sequential Preference Inference via Externalized Bayesian ComputationarXiv:2604.03925v2 Announce Type: replace Abstract: Large language models (LLMs) struggle to accumulate evidence across multiple rounds of user interactions, failing to update their beliefs in a manne
TechniqueMultimodal8 recent entries15 Oct 2026Empowering Edge Agents: A Systematic Analysis of Edge-Cloud Collaboration in LLM Agent ExecutionarXiv:2610.17816v1 Announce Type: new Abstract: Edge-cloud collaboration combines the lower inference overhead and greater data locality of edge-side execution with the stronger capabilities of cloud-→15 Oct 2026Don't Run with Scissors: Pruning Breaks VLA Models but They Can Be RecoveredarXiv:2510.08464v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models are a promising paradigm for field robotics, but their deployment is bottlenecked by strict edge SWaP-C co→15 Oct 2026Designing Textual Interfaces To Enhance Llm Reasoning On Audio-Visual Question AnsweringarXiv:2610.20085v1 Announce Type: cross Abstract: Automatic prompt optimization (APO) has shown strong effectiveness for text-based LLMs and LLM systems, but its application to audio-visual understand→15 Oct 2026CLIVO: Differentiable Cluster-Based Instruction Mixing with Learned Validation ObjectivesarXiv:2610.16876v1 Announce Type: new Abstract: Target-aware multimodal instruction selection requires useful examples and an appropriate balance of supervision. Sample-level rankings can overrepresen→15 Oct 2026Budgeted KV-Cache Repair for Evolving ContextsarXiv:2610.17338v1 Announce Type: new Abstract: Language-model agents revise their working context as information becomes obsolete, but deleting text does not erase its influence on cached computation→15 Oct 2026Beyond Size: How Gradients Shape Pruning Decisions in Large Language ModelsarXiv:2311.04902v3 Announce Type: replace Abstract: Large Language Models (LLMs) with billions of parameters are prime targets for network pruning, which removes some model weights without hurting per→15 Oct 2026Are Multimodal Benchmarks Really Useful? Item-Level Multimodal Benchmark Diagnosis via Structure-Response Co-CalibrationarXiv:2610.14542v1 Announce Type: new Abstract: Multimodal benchmarks are central to evaluating whether models can reason over information from multiple modalities. However, existing literature has re→15 Oct 2026Accelerating VLA Inference with Perturbation Informed ExecutionarXiv:2610.19656v1 Announce Type: new Abstract: Action-chunking vision-language-action (VLA) models predict sequences of future robot actions. Under fixed-horizon execution, the robot executes a fixed
TechniqueSafety8 recent entries15 Oct 2026CTIA-ODE: Continuous-Time Inter-Variable Attention for Long-Term Time Series ForecastingarXiv:2610.19831v1 Announce Type: new Abstract: Although multivariate time series forecasting has broad application prospects, effectively incorporating exogenous variables remains challenging. Prevai→15 Oct 2026Cross-Lingual Transfer of Evil Vectors Is Directionally AsymmetricarXiv:2610.17880v1 Announce Type: cross Abstract: Persona vectors are linear directions in the residual-stream activations of LLMs that encode behavioral traits and enable fine-grained control over mo→15 Oct 2026Correction Training for Diffusion ModelsarXiv:2610.14136v2 Announce Type: new Abstract: Iterative sampling in diffusion models can lead to error accumulation due to exposure bias. The denoiser is trained on real images interpolated with noi→15 Oct 2026Collective Learning for Unified Robotic Manipulation via Predictive Dynamics AdaptationarXiv:2610.19141v1 Announce Type: new Abstract: Learning a collective policy for state-based Cartesian manipulation across diverse robotic embodiments presents a fundamental challenge due to embodimen→15 Oct 2026Co-Evolving Acting and Forecasting for Language AgentsarXiv:2610.20597v1 Announce Type: cross Abstract: Training language agents is bottlenecked by the high cost of long-horizon rollouts, yet standard agentic reinforcement learning (RL) learns only from →15 Oct 2026Bellman Conformal Inference: Calibrating Prediction Intervals For Time SeriesarXiv:2402.05203v3 Announce Type: replace Abstract: We introduce Bellman Conformal Inference (BCI), a framework that wraps around any time series forecasting models and provides calibrated prediction →15 Oct 2026Alignment Faking - the Train -> Deploy Asymmetry: Through a Game-Theoretic Lens with Bayesian-Stackelberg EquilibriaarXiv:2511.17937v2 Announce Type: replace Abstract: Alignment faking is a form of strategic deception in AI in which models selectively comply with training objectives when they infer that they are in→15 Oct 2026AegisVox: Factorized Privacy and Clinical Preservation for Long-Form SpeecharXiv:2610.14643v1 Announce Type: new Abstract: Clinical speech reveals identity through both spoken identifiers and voice, yet its pauses, delivery, and speaker roles can also carry useful clinical e