{"total":13,"items":[{"citing_arxiv_id":"2605.15911","ref_index":42,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Statistical Inference for Smoothed Support Vector Machines in High Dimensions: From Offline to Online Data","primary_cat":"stat.ME","submitted_at":"2026-05-15T12:49:18+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A convolution-smoothed and debiased SVM estimator achieves asymptotic normality for statistical inference in high-dimensional offline and online settings.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12345","ref_index":21,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Output Composability of QLoRA PEFT Modules for Plug-and-Play Attribute-Controlled Text Generation","primary_cat":"cs.CL","submitted_at":"2026-05-12T16:21:43+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Summing outputs from separately trained QLoRA PEFT modules provides strong performance for attribute-controlled text generation, often matching or exceeding single-task modules even on single-attribute tests.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.11170","ref_index":236,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Unlearning with Asymmetric Sources: Improved Unlearning-Utility Trade-off with Public Data","primary_cat":"cs.LG","submitted_at":"2026-05-11T19:28:33+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"ALU uses public data to suppress unlearning cost quadratically while characterizing distribution mismatch effects, enabling mass unlearning with maintained utility.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.05870","ref_index":34,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"QuadraSHAP: Stable and Scalable Shapley Values for Product Games via Gauss-Legendre Quadrature","primary_cat":"cs.LG","submitted_at":"2026-05-07T08:36:50+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Shapley values in product games equal the integral of a degree-(d-1) polynomial over [0,1], allowing provably exact or near-exact computation via Gauss-Legendre quadrature with O(d m_q) work.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.01137","ref_index":17,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Metric-Normalized Posterior Leakage (mPL): Attacker-Aligned Privacy for Joint Consumption","primary_cat":"cs.LG","submitted_at":"2026-05-01T22:27:47+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"mPL measures attacker-aligned privacy leakage from joint data releases and AmPL provides an adaptive way to bound it with low utility cost in ML settings.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.18089","ref_index":265,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Towards E-Value Based Stopping Rules for Bayesian Deep Ensembles","primary_cat":"cs.LG","submitted_at":"2026-04-20T11:05:25+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"E-value sequential tests enable early stopping of MCMC sampling in Bayesian deep ensembles, often needing only a fraction of the full budget while improving over standard deep ensembles.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2408.07199","ref_index":122,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents","primary_cat":"cs.AI","submitted_at":"2024-08-13T20:52:13+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Agent Q integrates MCTS-guided search, self-critique, and off-policy DPO to train LLM agents that outperform behavior cloning and reinforced fine-tuning baselines in WebShop and achieve up to 95.4% success in real-world booking scenarios.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2405.17428","ref_index":154,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models","primary_cat":"cs.CL","submitted_at":"2024-05-27T17:59:45+00:00","verdict":"ACCEPT","verdict_confidence":"MODERATE","novelty_score":6.0,"formal_verification":"none","one_line_summary":"NV-Embed achieves first place on the MTEB leaderboard across 56 tasks by combining a latent attention layer, causal-mask removal, two-stage contrastive training, and data curation for LLM-based embedding models.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2402.11411","ref_index":40,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Aligning Modalities in Vision Large Language Models via Preference Fine-tuning","primary_cat":"cs.LG","submitted_at":"2024-02-18T00:56:16+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"POVID generates AI-created preference data to fine-tune vision-language models with DPO, reducing hallucinations and improving benchmark scores.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2310.16789","ref_index":122,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Detecting Pretraining Data from Large Language Models","primary_cat":"cs.CL","submitted_at":"2023-10-25T17:21:23+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Min-K% Prob detects pretraining data in LLMs by flagging outlier low-probability words in text, achieving 7.4% better performance than prior methods on the new WIKIMIA benchmark.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2308.10248","ref_index":84,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Steering Language Models With Activation Engineering","primary_cat":"cs.CL","submitted_at":"2023-08-20T12:21:05+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Activation Addition steers language models by adding contrastive activation vectors from prompt pairs to control high-level properties like sentiment and toxicity at inference time without training.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2304.06767","ref_index":131,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment","primary_cat":"cs.LG","submitted_at":"2023-04-13T18:22:40+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"RAFT aligns generative models by ranking samples with a reward model and fine-tuning only on the top-ranked outputs, reporting gains on reward scores and automated metrics for LLMs and diffusion models.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2004.05150","ref_index":58,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Longformer: The Long-Document Transformer","primary_cat":"cs.CL","submitted_at":"2020-04-10T17:54:09+00:00","verdict":"ACCEPT","verdict_confidence":"HIGH","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Longformer uses local windowed attention plus task-specific global attention to achieve linear scaling and state-of-the-art results on long-document language modeling, QA, and summarization after pretraining.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}