This paper proposes a method to estimate normal and shear pressures in prosthetic sockets using sparse sensing and mechanical models. By validating with global wrench and local interface loads, a quasi-static spring-mass contact model with least-squares parameter identification reduces measurement offsets, offering objective fit metrics.

This paper presents DLO-Lab, a differentiable simulator designed for deformable linear objects (e.g., ropes, cables, rubber bands). It models a wide range of material properties, provides a benchmark suite of tasks, and introduces a specialized agent to handle topological complexity and grasp sensitivity. Various policy-learning algorithms are evaluated, with sim-to-real transfer experiments.

This paper proposes a risk-aware model predictive control (RA-MPC) framework that incorporates prediction sets to guarantee risk control below a user-specified threshold without assumptions on the uncertainty distribution. By extending conformal risk control to general spectral risk measures, it achieves distribution-free risk quantification. Simulated vehicle obstacle avoidance scenarios demonstrate improved safety and reduced solve time compared to a baseline RA-MPC framework.

This paper presents Affordance2Action (A2A), a benchmark-centered learning framework for scene-level, task-conditioned part affordance grounding. Its core is A2A-Bench, a manipulation-oriented benchmark covering single-region and multi-region instruction correspondences in everyday scenes. Built with the A2A-AffordGen annotation pipeline, experiments show A2A exposes gaps in existing methods and improves task-level localization for downstream manipulation.

This paper proposes a distributed, risk-aware multi-agent NBV framework where each robot maintains a private local 3D Gaussian Splatting map and jointly maximizes expected information gain via Consensus ADMM, reducing communication by orders of magnitude while maintaining mapping quality and safety.

This study compares three haptic guidance models—spring-damper, potential field, and guiding tube—in teleoperation tasks. No universal best model is found: spring-damper excels in cluttered environments, potential field works well in free space but risks near obstacles, and guiding tube offers a balanced compromise. New objective metrics are proposed, showing that guiding force magnitude correlates with comfort and trust scores.

CLAW is a fully end-to-end self-supervised framework that learns world models and continuous latent action representations from action-free videos using adversarial latent regularization and diffusion-based generation. It enables imitation learning from observation and goal-directed planning, outperforming existing methods.

AgenticDiffusion is a multi-view UAV navigation framework that coordinates language-guided reasoning, open-vocabulary target grounding, vision-based diffusion planning, and NMPC. In 40 real-world trials, it achieved an 80% mission success rate and 100% trajectory generation success.

The paper introduces Spatial Artifact Coherence (SAC), a metric measuring when patch-based rPPG outperforms global methods under codec compression. Experiments on 280 subjects across 11 codec variants show SAC explains 93.8% of PCA advantage variance. Non-MPEG-4 codecs (SAC 0.10-0.18) achieve 84-90% PCA win rates, while MPEG-4 (SAC 0.48-0.59) only 61% with 5.8x reduction in improvement. P-Hybrid is identified as the most robust algorithm, with PatchPCA advantage requiring SAC<0.30 and low-to-moderate motion.

A new benchmark, GroupToM-Bench, evaluates multimodal large language models on group-level theory of mind. While models excel at individual mental state reasoning, they fail at understanding collective behavior that emerges nonlinearly from social tensions and structural constraints. The benchmark covers a causal chain from micro-level beliefs, desires, and intentions to group tension and macro-level outcomes, using a seven-level cognitive audit. Experiments reveal a significant gap between current models and human baselines.

This paper introduces Orli (Ordered Regression of Lines), an end-to-end model that unifies text line detection and reading order prediction as a single image-to-sequence task. Trained on 196,691 pages across ten writing systems, Orli marginally exceeds state-of-the-art on cBAD line detection without dataset-specific training, achieves near-perfect coverage and ordering on multiple reading-order benchmarks zero-shot, and adapts to specialized out-of-domain layouts with limited fine-tuning. Code and weights are open-sourced.

Pinpoint is a new image geolocation method that combines internet photos and street-view imagery using a retrieve-and-rerank architecture. It trains a contrastive embedder on both Flickr and street-view data to learn a shared image-GPS space, then uses an attention-based reranker to rescore candidates. Without relying on multimodal LLMs, it achieves state-of-the-art results on multiple benchmarks.

A diffusion model fine-tuned for single-image reflection separation, jointly generating transmission and reflection layers with a cross-layer self-attention mechanism and disjoint sampling strategy, achieving state-of-the-art performance on real-world benchmarks.

A new benchmark, EVID-Bench, assesses search-based video misinformation detection. It includes 222 videos with 9 manipulation types in 3 categories. The best model achieves only 61.43% point-level and 43.24% video-level accuracy, with AI-generated manipulations being especially challenging.

This paper proposes a new approach to optimal transport flow matching by treating the prior as a design choice rather than a fixed input, avoiding the intractable computation of OT coupling in high dimensions. The authors identify low-frequency projection of natural images as a prior that admits an OT-optimal identity coupling with data, reducing the flow matching task to synthesizing high-frequency details. The method requires no modifications to the flow model and integrates naturally with latent-space models, classifier-free guidance, and one-step generation frameworks. Across benchmarks, trajectory curvature is reduced by more than 2x, improving generation quality in the few-step regime.

This paper proposes IN2R, a novel framework that shifts from discrete selection to synthesizing continuous soft prototypes to rectify noisy correspondence in cross-modal retrieval, leveraging the geometric stability of intra-modal data for graph reasoning, achieving state-of-the-art performance on multiple datasets.

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.