The paper proposes SASA, a drift-resilient approach for weakly incremental learning in semantic segmentation. It uses learnable semantic anchors as rigid class-level references and elastic residual adaptation for stable yet flexible representation learning. A Spatial Label Arbitration mechanism filters noisy supervision and enforces the 'one object, one class' constraint. Experiments show state-of-the-art performance on standard benchmarks, especially in challenging multi-step incremental settings.

In embodied vision-language decision making tasks like robotic manipulation and navigation, VLMs and VLAs suffer from visual hallucinations due to inability to distinguish task-relevant objects from distractors. SceneDiver, a coarse-to-fine focus plan generation method, constructs a scene graph and progressively decomposes tasks to reduce hallucinations. A lightweight adapter distills this focus ability into VLAs for reactive control. Evaluations show reduced hallucinations and maintained efficiency.

MM-BizRAG is a novel multimodal retrieval-augmented generation approach for enterprise Q&A. It proactively extracts document structure via a structure-aware split and orientation-specific ingestion pipelines, enabling richer answers without finetuning. Experiments show up to 32% improvement over state-of-the-art baselines on enterprise and public benchmarks. The paper also introduces FastRAGEval, a cost-effective LLM judge metric. Accepted at ACL 2026 Industry Track.

This study investigates cross-prompt generalization in detecting AI-generated fake news using interpretable linguistic features such as lexical diversity, readability, and emotional intensity. A random forest classifier trained on one prompt's AI-generated articles and tested on another achieves AUC values between 0.988 and 1.000 across all six combinations, demonstrating robust detection under prompt variability.

This paper introduces ACAT, a web-based collaborative annotation tool that natively supports four ABSA workflows and provides an automated ETL pipeline to compute inter-annotator agreement metrics directly at export. Preliminary validation on 1,002 restaurant reviews shows a median annotation time of 31.58 seconds and IAA ranging from 0.78 to 0.86.

A large-scale empirical study assesses 284 interpretable linguistic features across 27 LLMs and ten text domains, finding that classifiers using only linguistic features can reliably distinguish AI-generated from human text, but many features are context-dependent while lexical richness remains robust across models and domains.

This study extends refusal steering methods to Mixture-of-Experts (MoE) large language models, demonstrating that steering performance is unaffected by the complex routing patterns of MoE. The authors propose two expert-aware refusal steering methods that leverage refusal-specific routing patterns and expert-specific directions to suppress normal refusal behavior. Results show that effective steering can be achieved based on a single expert's output, and that refusal signals differ from expert routing behavior, highlighting a significant role for attention.

A large-scale study finds that retrieval-augmented generation (RAG) yields only small and inconsistent improvements (1-2 points) over no-retrieval baselines in biomedical QA. The backbone model matters far more than retriever or corpus choice, and expert vs. layman sources perform similarly.

SALIMORY is a new framework that trains a single language model to manage cognitively-structured memory (user facts, preferences, working memory) for conversational agents, addressing the credit assignment bottleneck. Using hierarchical stage-wise process reward and reward-decomposed contrastive refinement, it supervises selective filtering, consolidation, and cue-driven recall end-to-end. It cuts memory-attributed failures by one-third, outperforms SOTA by over 10% in accuracy, and more than doubles the Good Personalization rate.

This article situates large language models (LLMs) within the longer history of computational approaches to concept analysis in the history, philosophy, and sociology of science (HPSS). It examines what LLMs add to existing methods, how they inherit longstanding problems, and reviews recent case studies. The first part reconstructs computational conceptual history before LLMs, covering early digital methods, distributional approaches, and lexical semantic change detection. The second part focuses on the LLM era, reviewing LLM-based work on lexical semantic change detection and relevant case studies, and revisiting methodological issues such as corpus construction, model choice, and operationalization.

A new study investigates how discourse-role labels such as 'Reference:', 'Instruction:', and 'Example:' affect language models' reliance on context. Using a paired fixed-content probe on 500 MMLU-Pro items, the researchers found that labels can shift misleading adoption rates by 56-84 percentage points. Labels like Instruction and Reference increase adoption, while Example suppresses it. The study recommends that RAG benchmarks report and control wrapper labels.

POLARIS is a training recipe for small open-weight models that significantly improves long-form creative writing. By combining a frontier LLM judge with human-reference injection in a GRPO framework, the resulting 9B model matches the performance of much larger models and exhibits strong length generalization.

arXiv:2606.04050v1 Announce Type: new Abstract: Existing quantization methods are fundamentally limited by rigid, integer-based bit-widths (e.g., 2, 3-bit), resulting in a ``deployment gap" where Large Language Models cannot be optimally fitted to specific memory budgets. To bridge this gap, we introduce LiftQuant, a novel framework that enables continuous bit-width control for true Pareto-optimal deployment. The core innovation is a ``lift-then-project" mechanism which approximates low-dimensional weight vectors by projecting a simple 1-bit lattice from a higher-dimensional ``lifted" space. Crucially, the effective bit-width is determined simply by the ratio of the lifted dimension to the original dimension, which allows the bit-width to be tuned quasi-continuous as the dimension is a fl…

This paper extends the Maximal Update Parametrization (μP) to Gated Delta Networks, an efficient linear architecture. By rigorously propagating coordinate-size estimates through the forward pass, gating mechanisms, and recurrent state dynamics, the authors derive scaling rules that enable stable learning-rate transfer across model widths under AdamW and SGD, whereas standard parametrization fails.

This paper defines Bayes-sufficient representations for a fixed supervised decision problem, introduces the Bayes quotient, and distinguishes sufficiency from minimality. Experiments validate the framework.

This paper presents a methodology for inverse design of critical experiments using deep neural network surrogate modeling and nonparametric gradient optimization to maximize neutronic similarity (c_k). The model combines a U-Net encoder-decoder with a novel multigroup attention pooling layer, enabling gradient-based optimization of material assignments in a geometry grid. Applied to a TN-LC transportation cask with HALEU fuel, the method achieves c_k scores of 0.97757, 0.81324, and 0.93276 for three configurations, demonstrating the potential of deep learning in accelerating nuclear technology validation.

A systematic study of projection sharing in the query-key-value (QKV) attention mechanism of transformers, showing that sharing key and value projections (Q-K=V) reduces KV cache by 50% with only 3.1% perplexity degradation. Combining with grouped-query attention (GQA) or multi-query attention (MQA) achieves 87.5% and 96.9% cache reduction, respectively, enabling practical on-device inference. Experiments span synthetic tasks, vision, and language modeling. Code is publicly available.

This paper presents a sharp pseudospectral analysis of transient amplification in coupled gradient descent algorithms, which are common in bilevel optimization, two-time-scale stochastic approximation, and adversarial training. The authors prove bounds on the Kreiss constant for block-triangular Jacobians and provide a finite-horizon iteration-complexity bound. Their theory reveals a non-asymptotic regime invisible to traditional spectral analysis, confirmed by experiments on linear-quadratic problems and neural network training.

This position paper argues that real-world RL systems must adopt continual learning over the train-then-fix paradigm, identifying four sources of post-deployment non-stationarity and highlighting successful continual RL examples.

The IEEE P3109 draft standard defines a parameterized family of binary floating-point formats and associated operations, tailored for machine learning. These formats allow efficient representation in few bits, with parameters including width, precision, signedness, and infinities. Operations are exception-free, using stochastic rounding, and signal exceptions via NaN. The standard also introduces kappa-approximation for approximate implementations and is mechanically verified.

A new study using XGBoost and eight routine clinical features from the ADNI dataset achieves high-precision three-class classification of normal cognition, mild cognitive impairment, and Alzheimer's disease, with a macro AUC of 0.982 and explainability via SHAP values.

This paper investigates the challenge of determining when to interrupt autonomous AI agents during long-horizon tasks. Using the HEART affective dynamics model, the authors evaluate four types of intervention triggers and report three major findings: a state saturation trap where frustration indicators quickly max out, a capability floor for LLM-based judges, and, most critically, very low inter-rater reliability among human annotators, questioning the validity of using single-annotator F1 scores as optimization targets.

This study examines how mathematicians use AI for formalizing mathematical proofs. Through surveys and a controlled user study, it finds that people desire AI assistance while retaining high-level control, using AI improves formalization accuracy, and users tend to employ multiple AI tools flexibly.

A new benchmark, Curation-Bench, tests whether generalist coding agents can autonomously curate training data. While out-of-the-box agents match published baselines within ten iterations, they tend to tune local variants rather than explore new policy families. Scaffolded agents that require citing and adapting prior methods autonomously discover a policy that outperforms baselines at one-tenth the data budget, suggesting that structured method adaptation is key for reliable data curation automation.

StepPRM-RTL is a novel framework that combines stepwise trajectory modeling, process-reward modeling (PRM), and retrieval-augmented fine-tuning (RAFT) to enhance LLM-based RTL code generation. It achieves over 10% improvement in functional correctness and reasoning fidelity over prior methods on Verilog and VHDL benchmarks.

Multimodal large language models are increasingly capable of complex reasoning, yet their performance often degrades when they must externalize a problem through a tool and then reason over the tool's output, specifically when relying on visual aids. To study this discrepancy, we introduce VAMPS (Visual-Assisted Mathematical Problem Solving), a benchmark for graph-assisted mathematics. VAMPS contains 1,168 multimodal, bilingual multiple-choice question-answer pairs drawn from Iranian University Entrance Exam algebra and calculus problems, expanded with human-reviewed LLM-generated synthetic variants. Overall, we found that direct analytical solving surprisingly outperforms tool-enabled visual solving, even on problems where plotting is a natural strategy.

SMAC-Talk extends the StarCraft Multi-Agent Challenge with a natural language communication channel to evaluate LLM-based agents in cooperative multi-agent settings. It features decentralized control, partial observability, long-horizon decision making, and scenarios with deceptive communicators. Benchmarking using Qwen3.5 models reveals how reasoning, memory, and scale affect coordination.

LLMs are reshaping research while eroding epistemic accountability. The PEEL framework combines deterministic distant reading with LLM interpretation, grounded in Peircean semiotics, to reveal systematic distortions in AI-generated text. Key implications: deterministic tools must accompany AI, fluency does not equal fidelity, and epistemic authority must be designed in.

This paper challenges the common assumption that AI emotional support is a deliberate act. It argues that AI emotional support often emerges incidentally during task-oriented interactions on general-purpose platforms, and these positive experiences can path-dependently shift preferences away from humans toward AI. A 28-day longitudinal study with OpenAI found that daily 5-minute AI conversations led to a 10.3% decrease in preference for human support and an 11.6% increase for AI. The authors conclude that current policies focused on companion apps are inadequate and must be extended to general-purpose AI systems to address cumulative behavioral changes.

This paper proposes an ontology-grounded verification framework for pre-deployment assurance of enterprise AI agents. The framework combines an Agent Operational Envelope, an ontology-to-scenario generation pipeline, and a Trust Certificate. A pilot in four regulated industries across the US and Vietnam generated 1,800 scenarios and showed ontology-grounded generation achieved 48.3% regulatory coverage versus 33.1% for a persona-based baseline, with the highest domain specificity.