{"total":28,"items":[{"citing_arxiv_id":"2605.22263","ref_index":4,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Tailoring Teaching to Aptitude: Direction-Adaptive Self-Distillation for LLM Reasoning","primary_cat":"cs.LG","submitted_at":"2026-05-21T10:07:46+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"DASD improves math reasoning in LLMs by adaptively directing self-distillation based on per-token entropy to balance exploration and step accuracy, outperforming prior self-distillation and RLVR baselines on six benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.20151","ref_index":24,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"When Does Model Collapse Occur in Structured Interactive Learning?","primary_cat":"cs.LG","submitted_at":"2026-05-19T17:41:09+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Model collapse occurs in structured interactive learning if and only if the directed interaction graph satisfies a specific topological condition, with finite-sample guarantees for linear regression and asymptotic results for M-estimators.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.17558","ref_index":21,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Firefly: Illuminating Large-Scale Verified Tool-Call Data Generation from Real APIs","primary_cat":"cs.SE","submitted_at":"2026-05-17T17:38:17+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"FireFly inverts task synthesis by exploring real MCP servers first via pairwise tool graphs and sub-DAG sampling, then generates 5,144 verified tasks backward from outcomes to train a 4B model that matches Claude Sonnet 4.6 on tool-calling benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.17172","ref_index":92,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"OpenJarvis: Personal AI, On Personal Devices","primary_cat":"cs.LG","submitted_at":"2026-05-16T22:00:10+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"OpenJarvis decomposes personal AI into Intelligence, Engine, Agents, Tools & Memory, and Learning primitives and applies LLM-guided spec search to produce on-device configurations that reach within 3.2 pp of cloud baselines on average across eight tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12652","ref_index":4,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Multi-Rollout On-Policy Distillation via Peer Successes and Failures","primary_cat":"cs.LG","submitted_at":"2026-05-12T18:57:44+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.11290","ref_index":35,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"ReAD: Reinforcement-Guided Capability Distillation for Large Language Models","primary_cat":"cs.CL","submitted_at":"2026-05-11T22:17:51+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"ReAD applies a contextual bandit to allocate fixed-token distillation budget across interdependent LLM capabilities, yielding higher task utility and fewer negative spillovers than standard methods.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"[33] Can Xu, Qingfeng Sun, Kai Zheng, Xiubo Geng, Pu Zhao, Jiazhan Feng, Chongyang Tao, and Daxin Jiang. Wizardlm: Empowering large language models to follow complex instructions. arXiv preprint arXiv:2304.12244, 2023. [34] Qiantong Xu, Fenglu Hong, Bo Li, Changran Hu, Zhengyu Chen, and Jian Zhang. On the tool manipulation capability of open-source large language models, 2023. [35] Xiaohan Xu, Ming Li, Chongyang Tao, Tao Shen, Reynold Cheng, Jinyang Li, Can Xu, Dacheng Tao, and Tianyi Zhou. A survey on knowledge distillation of large language models.arXiv preprint arXiv:2402.13116, 2024. [36] Fanjia Yan, Huanzhi Mao, Charlie Cheng-Jie Ji, Tianjun Zhang, Shishir G. Patil, Ion Stoica, and Joseph E. Gonzalez. Berkeley function calling leaderboard."},{"citing_arxiv_id":"2605.08873","ref_index":32,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"CoDistill-GRPO: A Co-Distillation Recipe for Efficient Group Relative Policy Optimization","primary_cat":"cs.LG","submitted_at":"2026-05-09T10:51:58+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"CoDistill-GRPO lets small and large models mutually improve via co-distillation in GRPO, raising small-model math accuracy by over 11 points while cutting large-model training time by about 18%.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.08568","ref_index":54,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Different Prompts, Different Ranks: Prompt-aware Dynamic Rank Selection for SVD-based LLM Compression","primary_cat":"cs.LG","submitted_at":"2026-05-09T00:02:33+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"PARSE trains a prompt-aware linear router on dense-model outputs to select dynamic SVD ranks, improving accuracy up to 10% at 0.6 compression ratio on LLaMA-7B while delivering 2.5x prefill and 2.4x decode speedups.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"InProceedings of the AAAI Conference on Artificial Intelligence, volume 37, pages 10566-10575, 2023. 13 [52] Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531, 2015. [53] Yuxian Gu, Li Dong, Furu Wei, and Minlie Huang. Minillm: Knowledge distillation of large language models.arXiv preprint arXiv:2306.08543, 2023. [54] Xiaohan Xu, Ming Li, Chongyang Tao, Tao Shen, Reynold Cheng, Jinyang Li, Can Xu, Dacheng Tao, and Tianyi Zhou. A survey on knowledge distillation of large language models.arXiv preprint arXiv:2402.13116, 2024. [55] Geonhwa Jeong, Po-An Tsai, Abhimanyu R Bambhaniya, Stephen W Keckler, and Tushar Kr- ishna. Enabling unstructured sparse acceleration on structured sparse accelerators."},{"citing_arxiv_id":"2605.07783","ref_index":16,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Chain-based Distillation for Effective Initialization of Variable-Sized Small Language Models","primary_cat":"cs.CL","submitted_at":"2026-05-08T14:21:05+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Chain-based Distillation constructs a sequence of anchor models to enable efficient initialization of variable-sized SLMs through interpolation, with bridge distillation for cross-architecture transfer, yielding better performance than scratch training.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.07725","ref_index":9,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"SOD: Step-wise On-policy Distillation for Small Language Model Agents","primary_cat":"cs.CL","submitted_at":"2026-05-08T13:30:42+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"SOD reweights on-policy distillation strength step-by-step using divergence to stabilize tool use in small language model agents, yielding up to 20.86% gains and 26.13% on AIME 2025 for a 0.6B model.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"[7] Shengda Fan, Xuyan Ye, Yupeng Huo, Zhi-Yuan Chen, Yiju Guo, Shenzhi Yang, Wenkai Yang, Shuqi Ye, Jingwen Chen, Haotian Chen, et al. Agentprocessbench: Diagnosing step-level process quality in tool-using agents.arXiv preprint arXiv:2603.14465, 2026. [8] Jiajun Xu, Zhiyuan Li, Wei Chen, Qun Wang, Xin Gao, Qi Cai, and Ziyuan Ling. On-device language models: A comprehensive review.arXiv preprint arXiv:2409.00088, 2024. [9] Xiaohan Xu, Ming Li, Chongyang Tao, Tao Shen, Reynold Cheng, Jinyang Li, Can Xu, Dacheng Tao, and Tianyi Zhou. A survey on knowledge distillation of large language models.arXiv preprint arXiv:2402.13116, 2024. [10] Jiahao Qiu, Xinzhe Juan, Yimin Wang, Ling Yang, Xuan Qi, Tongcheng Zhang, Jiacheng Guo, Yifu Lu, Zixin Yao, Hongru Wang, et al. Agentdistill: Training-free agent distillation with"},{"citing_arxiv_id":"2605.07711","ref_index":3,"ref_count":2,"confidence":0.98,"is_internal_anchor":true,"paper_title":"SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation","primary_cat":"cs.CL","submitted_at":"2026-05-08T13:16:17+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"SimCT enlarges the supervision space in cross-tokenizer on-policy distillation using short jointly tokenizable multi-token continuations, producing consistent gains over shared-token baselines on math and code benchmarks.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"path for cross-tokenizer OPD. 9 References [1] Geoffrey E. Hinton, Oriol Vinyals, and Jeffrey Dean. Distilling the knowledge in a neural network.arXiv preprint, arXiv:1503.02531, 2015. [2] Xunyu Zhu, Jian Li, Yong Liu, Can Ma, and Weiping Wang. A survey on model compression for large language models.Transactions of the Association for Computational Linguistics (TACL), 2024. [3] Xiaohan Xu, Ming Li, Chongyang Tao, Tao Shen, Reynold Cheng, Jinyang Li, Can Xu, Dacheng Tao, and Tianyi Zhou. A survey on knowledge distillation of large language models.arXiv preprint, arXiv:2402.13116, 2024. [4] Chuanpeng Yang, Wang Lu, Yao Zhu, Yidong Wang, Qian Chena, Chenlong Gao, Bingjie Yan, and Yiqiang Chen. Survey on knowledge distillation for large language models: Methods,"},{"citing_arxiv_id":"2605.06597","ref_index":11,"ref_count":2,"confidence":0.98,"is_internal_anchor":true,"paper_title":"UniSD: Towards a Unified Self-Distillation Framework for Large Language Models","primary_cat":"cs.CL","submitted_at":"2026-05-07T17:22:11+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"UniSD unifies self-distillation components for autoregressive LLMs and its full integrated version improves base models by 5.4 points and baselines by 2.8 points across six benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.06387","ref_index":6,"ref_count":3,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Asymmetric On-Policy Distillation: Bridging Exploitation and Imitation at the Token Level","primary_cat":"cs.LG","submitted_at":"2026-05-07T15:02:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"AOPD modifies on-policy distillation by using localized divergence minimization for non-positive advantages instead of negative reinforcement, yielding average gains of 4.09/8.34 over standard OPD on math reasoning benchmarks under strong/weak initialization.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.05893","ref_index":91,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Logic-Regularized Verifier Elicits Reasoning from LLMs","primary_cat":"cs.CL","submitted_at":"2026-05-07T09:03:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"LOVER creates an unsupervised logic-regularized verifier that reaches 95% of supervised verifier performance on reasoning tasks across 10 datasets.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.25110","ref_index":4,"ref_count":2,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Knowledge Distillation Must Account for What It Loses","primary_cat":"cs.LG","submitted_at":"2026-04-28T01:32:46+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Knowledge distillation evaluations must report lost teacher capabilities via a Distillation Loss Statement rather than relying solely on task scores.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.19144","ref_index":24,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"ReflectMT: Internalizing Reflection for Efficient and High-Quality Machine Translation","primary_cat":"cs.CL","submitted_at":"2026-04-21T06:48:41+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"ReflectMT internalizes reflection via two-stage RL to enable direct high-quality machine translation that outperforms explicit reasoning models like DeepSeek-R1 on WMT24 while using 94% fewer tokens.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.07941","ref_index":15,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning","primary_cat":"cs.CL","submitted_at":"2026-04-09T08:00:37+00:00","verdict":"ACCEPT","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"LLM post-training is unified as off-policy or on-policy interventions that expand support for useful behaviors, reshape policies within reachable states, or consolidate behavior across training stages.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"− − − −Direct preference optimization, preference optimization variants, benchmarking, applications, and open challenges RLHF / alignment[13, 29] − − − ◦LLM alignment methods, RLHF, evaluation, and RLHF limitations / open problems Process / verifier[5, 30]− ◦ − ◦ Process reward modeling, process supervision, verifier engineering, and verifier-guided post-training Distillation[15]− ◦ • −Teacher-student transfer, compression, self-improvement, and knowledge distillation methods General post-training [31] − − − −Broad post-training taxonomy spanning fine-tuning, alignment, reasoning, efficiency, and integration / adaptation Post-training scaling [32] − − − −Post-training scaling via SFT, RLxF, and test-time compute, emphasizing scalable"},{"citing_arxiv_id":"2604.03841","ref_index":49,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Training a Student Expert via Semi-Supervised Foundation Model Distillation","primary_cat":"cs.CV","submitted_at":"2026-04-04T19:45:25+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A semi-supervised framework distills vision foundation models into compact instance segmentation experts that outperform their teachers by up to 11.9 AP on Cityscapes and 8.6 AP on ADE20K while being 11 times smaller.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.02753","ref_index":20,"ref_count":2,"confidence":0.9,"is_internal_anchor":true,"paper_title":"DeCo-DETR: Decoupled Cognition DETR for efficient Open-Vocabulary Object Detection","primary_cat":"cs.CV","submitted_at":"2026-04-03T05:56:29+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"DeCo-DETR builds hierarchical semantic prototypes offline and uses decoupled training streams to deliver competitive zero-shot open-vocabulary detection with improved inference speed.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2601.20375","ref_index":50,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"LLM-AutoDP: Automatic Data Processing via LLM Agents for Model Fine-tuning","primary_cat":"cs.LG","submitted_at":"2026-01-28T08:37:34+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"LLM agents iteratively generate and optimize data processing strategies for fine-tuning, delivering over 80% win rates versus unprocessed data and 65% versus LLM-based AutoML baselines while cutting search time by up to 10x.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2601.09722","ref_index":9,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"ADMEDTAGGER: an annotation framework for distillation of expert knowledge for the Polish medical language","primary_cat":"cs.CL","submitted_at":"2025-12-27T10:00:52+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Llama 3.1 annotates Polish medical texts to train DistilBERT classifiers achieving F1 scores above 0.80 that are 500 times smaller than the teacher model.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2510.18471","ref_index":28,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"CodeRL+: Improving Code Generation via Reinforcement with Execution Semantics Alignment","primary_cat":"cs.SE","submitted_at":"2025-10-21T09:48:06+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"CodeRL+ integrates variable-level execution trajectory inference into RLVR training to align textual code representations with execution semantics, delivering 4.6% relative pass@1 gains and generalization to code-reasoning and test-output tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2508.18958","ref_index":38,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"A drone-based framework for coral habitat mapping via weakly supervised segmentation","primary_cat":"cs.CV","submitted_at":"2025-08-26T11:58:50+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A multi-scale weakly supervised framework converts underwater point classifications into coarse masks to train UAV coral segmentation models, then refines them via self-training to reach 86.07% pixel accuracy and 52.23% mIoU without pixel-level labels.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2508.03949","ref_index":36,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Model Compression vs. Adversarial Robustness: An Empirical Study on Language Models for Code","primary_cat":"cs.SE","submitted_at":"2025-08-05T22:32:32+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Empirical tests show compressed code language models retain task performance but suffer markedly lower robustness under four standard adversarial attacks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2505.17138","ref_index":34,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"RAP: Runtime Adaptive Pruning for LLM Inference","primary_cat":"cs.LG","submitted_at":"2025-05-22T06:12:42+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"RAP is a reinforcement learning framework for runtime-adaptive pruning of LLMs that jointly optimizes model weights and KV-cache usage under varying memory budgets.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2505.15925","ref_index":46,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"VERDI: VLM-Embedded Reasoning for Autonomous Driving","primary_cat":"cs.RO","submitted_at":"2025-05-21T18:24:36+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"VERDI aligns perception, prediction, and planning outputs of end-to-end AD models with VLM-generated text features at training time to embed structured reasoning, yielding up to 11% better l2 distance and 10% higher non-collision rate in closed-loop tests.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2502.21074","ref_index":130,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation","primary_cat":"cs.CL","submitted_at":"2025-02-28T14:07:48+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"CODI compresses explicit CoT into continuous space via self-distillation and is the first implicit method to match explicit CoT performance on GSM8k at GPT-2 scale with 3.1x compression and 28.2% higher accuracy than prior implicit approaches.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2502.03814","ref_index":128,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Large Language Models for Multi-Robot Systems: A Survey","primary_cat":"cs.RO","submitted_at":"2025-02-06T06:52:14+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"A survey that categorizes LLM uses in multi-robot systems across task allocation, motion planning, action generation, and human interaction, while noting challenges and future research opportunities.","context_count":1,"top_context_role":"background","top_context_polarity":"support","context_text":"how smaller architectures can reduce computa- tional demands and latency while maintaining adequate performance for specific tasks. Model distillation is another approach to make small models more capable by distilling knowledge from a more capable LLM, like DeepSeek-R1-Distill- Qwen-1.5B, where the knowledge from DeepSeek R1 is distilled into a small Qwen2.5-Math-1.5B model [128]. Balancing efficiency and effective- ness is key to enabling scalable deployments of LLMs in field robotics. Multi-modal and Embodied Extensions. Emerging research on multi-modal LLMs sug- gests promising opportunities for extending MRS capabilities. Video-language transformers, point cloud-language models [26], and spatio-temporal VLAs could enable richer reasoning over dynamic"}],"limit":50,"offset":0}