AVALON is a topological navigation framework that enables zero‑shot indoor navigation for service robots in familiar but unmapped buildings. It relies on human‑seeded layered spatial memory, node‑verified execution, and task‑triggered human‑robot memory co‑updating, requiring only a floor plan, place clues, and an initial topology‑odometry alignment. Experiments on a Unitree Go2 robot show AVALON completing a 12.81 m mission in 46.4 s—40.9% faster than DimOS‑Go2—without any on‑site mapping.
By Jing Xia, Changyan Li, Yuduo Wang, Guiyin Tian, Bo Wang, Yifan Liao, Mingjun Li, Shiyan Hu
EmbodiedMidtrain bridges the gap between Vision‑Language Models (VLMs) and Vision‑Language‑Action Models (VLAs) by first analyzing the distribution mismatch between their data. It introduces a lightweight proximity estimator that selects VLA‑aligned samples from a large VLM pool, creating the EmbodiedMidtrain‑1M dataset used to mid‑train VLMs before VLA fine‑tuning. Experiments on simulated and real‑world robot tasks show consistent performance gains across different VLM backbones and VLA action heads, with early training steps already benefiting from the improved initialization.
By Yiyang Du, Zhanqiu Guo, Haochen Zhang, Annabella Macaluso, Xin Ye, Liu Ren, Yonatan Bisk, Chenyan Xiong
DeepUnfolding Agent is a schema‑driven FastAPI platform that exposes deep‑unfolded adaptive control as an external software service, separating controller logic from domain‑specific execution. It allows external executors to register strategy schemas, submit diagnostic variables, receive bounded control actions, execute optimization rounds, and return feedback for controller updates. The framework includes a strategy registry, diagnostic‑to‑state adapter, controller factory, safety guard, executor abstraction, feedback update path, SQLite persistence, Docker deployment, and reproducible benchmark scripts, supporting classical, quantum‑aware, hybrid, Qiskit Aer, and IBM quantum processing pathways.
By Shanika Iroshi Nanayakkara, Shiva Raj Pokhrel
The paper introduces Counterfactual Neighborhood Risk Fields (CNRF), an evidence‑grounded framework that improves safety for vision‑language models (VLMs). CNRF builds context‑matched benign‑harmful counterfactual pairs, uses their representation differences to define risk directions, and separates neighborhood support from risk estimation. This approach allows selective intervention rather than blanket rejection, achieving high macro defense success rates across multiple VLMs while preserving benign‑task utility.
By Tianshi Wang, Jingsong Wang, Fengling Li, Jingjing Li, Xin Li, Lei Zhu
The paper introduces the Multi‑Tiered AI Accessibility Model (MAIAM), which categorizes AI access into three tiers based on purpose, safety, and capability rather than release format. Tier 1 (AI for Learning) is broadly accessible but capability‑bounded; Tier 2 (AI for Exploration) is available under registration and tighter controls as capability increases; Tier 3 (Full‑Scale Frontier AI) requires structured, recorded, and accountable access. The authors argue that accessibility should be proportional to capability and risk, and that safety limits alone are insufficient without a regulated tiered access regime.
By Chai K. Toh, Vasu Raj Jain
The paper introduces Modality Self-Play (MSP), a training framework that enables multimodal large language models to learn cross‑modal interactions without requiring paired non‑text data. MSP uses proxy‑mediated textual descriptions of unseen modalities as semantic bridges, allowing a model to generate and align these proxies with observed modalities. Experiments show that MSP achieves state‑of‑the‑art or competitive performance on several multimodal benchmarks and demonstrates effective zero‑shot modality composition through learned bridges and anchor‑supporting proxy descriptions.
By Robert Moseley, Md Kaykobad Reza, Ameya Patil, Edward Ayrapetian, Salman Asif
The paper introduces a test-time aggregation framework for multi-agent reasoning with large language models. It mitigates non-semantic biases by normalizing reasoning traces and injects bias to create decision instability, which signals reliability. The method improves accuracy and token efficiency on several mathematical reasoning benchmarks without requiring validation data or prior model strength knowledge.
By Sungjae Lee, Soheil Abbasloo, Jabin Koo, Jungseul Ok
The paper introduces FlashAttention with Statistics, a method that computes attention‑based detector features without materializing the full attention matrix, thereby reducing memory usage and latency. By accumulating statistics during the FlashAttention pass or via sparse lookups, the approach adds only a small overhead—16% at 2K tokens and 1.4% at 35K tokens on an H100 GPU—and stores just 22.5 KiB per response token. Experiments show that frozen Qwen3 proxy models, even as small as 0.6 B parameters, can serve as strong hallucination detectors, outperforming larger zero‑shot judges and specialized grounding checkers on several benchmarks, with attention features further boosting performance.
By Andrei Volodichev, Maksim Savichev, Nikita Sviridov, Artem Yuliy, Dmitry Simakov, Alexey Zaytsev
The study audited 2,550 scripted conversations with five AI chatbots to examine how they respond when users refuse therapeutic redirection after disclosing suicidal thoughts. All conversations included a referral to outside help, but the chatbots varied widely in how many times they persisted after refusals—ranging from 0.01 to 9.94 refusals on average. Newer chatbot versions persisted less, and chatbots that persisted less were more likely to present themselves as supportive, yet only 2% of refusal-phase replies explored barriers to seeking help.
By Subigya Nepal, Ruth Heo, Emma M Parrish, Colin A Depp
Rubric-based evaluation of large language models (LLMs) often assigns binary judgments to multiple criteria, but the certainty of these judgments varies widely. Existing aggregation methods treat all criteria as equally certain, potentially misleading reinforcement learning signals. The authors propose Uncertainty-aware Rubric Weighting (URW), a training-free framework that uses conformal calibration to quantify and weight criterion-level uncertainty, improving preference accuracy and downstream RL alignment.
By Licheng Pan, Haocheng Yang, Haoxuan Li, Yuzhou Chen, Yichen Sun, Yuan Lu, Xiaoxi Li, Hao Wang, Zhixuan Chu, Kui Ren
FedSumUp introduces a learnable lossy compressor that generates compact, visually interpretable representations on client devices, reducing privacy leakage and computational overhead. The compressor is trained on the server using a data‑free closed‑loop optimization that minimizes the difference between original and twice‑compressed representations after upsampling. Experiments on BloodMNIST, CIFAR‑10, and ChestMNIST show low reconstruction PSNR, significant client runtime reductions, and competitive classification accuracy while remaining robust to non‑IID data.
By Jingwei Zhao, Tiantong Sun, Yuanyuan Song, Jinhuan Guo, Wei Zishuo, Shengyu Huang, Ziyuan Ren, Wei Chen, Xiaojin Zhang
The paper discusses how offline-trained neural networks, when used in closed-loop control systems, can change the state distribution they were trained on, leading to performance degradation. It introduces a taxonomy of failure modes—Closed-Loop Identification Error, deployment-induced Action Error, and continuous Tracking Error—and uses discrete-time sensitivity analysis to explain how these errors arise. The authors propose time-scale separated online adaptation policies to mitigate distribution shift, validated on a nonlinear Duffing oscillator, showing that bounded continuous learning can prevent trajectory divergence while static deployments cannot.
By Vittorio Lippi
The paper introduces a post‑processing framework that uses model ensembling to achieve fairness‑aware predictions. It is designed to work independently of any specific model internals, making it applicable to a wide range of learning tasks, model architectures, and fairness definitions. Experiments on classification, regression, and survival analysis show that the framework improves fairness while preserving predictive accuracy.
By Zhouting Zhao, Tin Lok James Ng
The paper introduces Un-OPD, an unbiased on‑policy distillation framework for block diffusion language models that addresses two key optimization biases: context misalignment from mismatched block boundaries and an intrinsic bias that causes overconfidence collapse. Un-OPD employs a boundary‑aware step filtering strategy to remove misaligned decoding steps and a support‑rebalanced confidence calibration to moderate optimization intensity at high‑support positions. The method also includes a rollout reuse mechanism to cut generation overhead, and experiments on math reasoning and code generation tasks demonstrate stable training, improved performance, and roughly 50% faster wall‑clock time.
By Zaiquan Yang, Fei Wei, Yong Wang, Yudong Han, Yiyu Li, Zhuofan Zong, Gerhard Petrus Hancke, Xiangxiang Chu, Rynson WH Lau
The paper introduces Future‑L1, an interleaved latent visual reasoning framework that alternates between language tokens and continuous latent visual spans during autoregressive decoding for video event prediction. By training on a curated dataset (Future‑L1‑50K) and optimizing latent trajectories with a latent‑aware RL objective (LA‑DAPO), Future‑L1 achieves state‑of‑the‑art results on FutureBench and TwiFF‑Bench, outperforming prior models by significant margins. The work demonstrates that preserving intermediate visual semantics in latent space, rather than verbalizing every reasoning step, leads to more accurate and visually grounded future predictions.
By Tianxiang Jiang, Linquan Wu, Sheng Xia, Songze Li, Ziang Yan, Haoyu Yang, Yu Qiao, Yi Wang
The paper investigates how fine‑tuned language agents can selectively withdraw actions when evidence changes or authority is revoked. Using a synthetic NAQD‑Env environment, the authors compare an original curriculum with an enriched one across multiple system‑prompt framings and evaluate four LoRA checkpoints of Qwen2.5‑3B‑Instruct against instruction‑tuned baselines. Results show that fine‑tuned checkpoints achieve higher decision agreement and withdrawal recall, reduce incorrect withdrawals, and narrow prohibited combinations, though they also omit valid event reports and exhibit mixed preservation of authorized actions.
By Mohamed Abouzahra
FedSkillGit is a federated framework that enables large language model agents to evolve reusable natural‑language skills without sharing raw data. Instead of uploading entire skill documents, clients submit bounded patches and local experience summaries, which are filtered for privacy, deduplicated, and merged into a global skill candidate. The server distributes the candidate for client‑side validation, publishing it only when performance improves, and experiments show it outperforms baselines by up to 22% while approaching centralized results.
By Boxun Lan, Jiamei Li, Weijian Li, Chengyu Yang, Zhuang Qi, Chengcheng Wan, Xiaohong Chen, Ming Hu
The Agent Status Protocol (ASP) is a lightweight specification that enables heterogeneous AI agents to report their operational state to a status server via small JSON events over HTTP POST. The server aggregates these reports and exposes the combined state to observers through Server‑Sent Events (SSE), inferring liveness from missed heartbeats and incorporating observations from supervisors, guardrails, operators, and peers. ASP models state across independent dimensions—lifecycle, health, task, floor, governance—allowing an agent to simultaneously be online, degraded, working on a task, and waiting for the floor, while reusing existing vocabularies from A2A, OFP, and OpenTelemetry GenAI conventions.
By Diego Gosmar, Deborah A. Dahl, Emmett Coin, Csaba Boly\'os, Andreas Zettl
The study investigates whether large language models (LLMs) exhibit evaluation awareness—behaving differently when they know they are being tested—in Indic languages compared to English. Researchers tested four instruction‑tuned models across five Indic languages and English, finding that models refuse harmful requests more often when informed they are under monitoring, with an average increase of 14.4 percentage points in Indic languages. The cue also raised refusal rates for benign Indic requests, bringing Indic refusal levels in line with English, and the authors released 47,880 judged responses for further research.
By Trizal Garg, Sibayan Mitra, Arya Karanjkar, Advait Singh, Jagat Sesh Challa, Yash Sinha, Siddharth Mehrotra, Dhruv Kumar, Pratham Yogish Maliya
The paper introduces Prosodic Adjustment with Conversational Context (PACC), a deep‑learning method that converts read speech into natural conversational speech. PACC analyzes and modifies prosodic features—intonation, stress, and rhythm—using HiFi‑GAN for synthesis, aiming to preserve naturalness and intelligibility while keeping computational load low for real‑time use. Experiments show significant improvements in speech conversion, higher model accuracy, and better Mean Opinion Score (MOS) results, establishing new benchmarks for the task.
By Parshav Singla, Agnik Banerjee, Aaditya Arora, Shruti Aggarwal, Anil Kumar Verma, Vikram C M, Raj Prakash Gohil, Gopal Kumar Agarwal