{"total":16,"items":[{"citing_arxiv_id":"2605.27968","ref_index":32,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Adapting Automotive Aerodynamics Surrogates to New Vehicle Families via Transfer Learning","primary_cat":"cs.CE","submitted_at":"2026-05-27T05:03:25+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"LoRA adapters enable a 61.47M-parameter aerodynamics Transformer pretrained on four vehicle families to adapt to a held-out fifth family with 20 samples, reaching R²=0.85 and outperforming full fine-tuning and from-scratch training with 3x more data.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.02606","ref_index":36,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"ReLoRA: Knowledge-Reusing Adaptation for Fast Rollout of Evolving LLM Services","primary_cat":"cs.LG","submitted_at":"2026-05-23T15:56:16+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"ReLoRA reduces time-to-readiness for LoRA adapters on updated LLMs by up to 8.9x through adaptive Bayesian initialization and scheduled regularization while improving accuracy by up to 4.6%.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.13421","ref_index":151,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Combining pre-trained models via localized model averaging","primary_cat":"stat.ME","submitted_at":"2026-05-13T12:16:04+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Localized model averaging with covariate-dependent weights achieves asymptotic optimality and weight consistency for combining pre-trained models under a general loss framework.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.09781","ref_index":43,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Parameter-Efficient Neuroevolution for Diverse LLM Generation: Quality-Diversity Optimization via Prompt Embedding Evolution","primary_cat":"cs.NE","submitted_at":"2026-05-10T22:00:15+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"QD-LLM applies neuroevolution to prompt embeddings within a quality-diversity framework, producing 46% higher coverage and 41% higher QD-score than QDAIF on HumanEval, MBPP, and creative writing benchmarks.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Recent work has begun exploring QD for text generation. Quality-Diversity through AI Feedback (QDAIF) [4] demonstrated QD using LLMs as both generators and behavior evaluators, achieving diverse story generation. Quality Diversity through Human Feedback (QDHF) [12] showed that diversity metrics can be effectively inferred for generative models. Language Model Crossover (LMX) [43] introduced LLM-based variation operators for evolutionary optimization. FunSearch [51] achieved mathemat- ical discoveries through evolutionary code generation. However, these approaches use LLMs asfixedblack-box generators without evolving any neural parameters, limiting their integration with the broader neuroevolution paradigm that has historically evolved"},{"citing_arxiv_id":"2605.05659","ref_index":30,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Structural Correspondence and Universal Approximation in Diagonal plus Low-Rank Neural Networks","primary_cat":"cs.LG","submitted_at":"2026-05-07T04:21:04+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Diagonal plus Low-Rank (DLoR) neural networks achieve universal approximation for general activations by additive or multiplicative decompositions of full-rank transformations.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.27818","ref_index":31,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"MASCing: Configurable Mixture-of-Experts Behavior via Activation Steering Masks","primary_cat":"cs.CR","submitted_at":"2026-04-30T12:58:57+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"MASCing uses an LSTM surrogate and optimized steering masks to enable flexible, inference-time control over MoE expert routing for safety objectives, improving jailbreak defense and content generation success rates substantially across multiple models.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.19342","ref_index":43,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Are Large Language Models Economically Viable for Industry Deployment?","primary_cat":"cs.CL","submitted_at":"2026-04-21T11:25:22+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Small LLMs under 2B parameters achieve better economic break-even, energy efficiency, and hardware density than larger models on legacy GPUs for industrial tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2602.20409","ref_index":35,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"CLIPoint3D: Language-Grounded Few-Shot Unsupervised 3D Point Cloud Domain Adaptation","primary_cat":"cs.CV","submitted_at":"2026-02-23T23:17:12+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"CLIPoint3D is the first CLIP-based framework for few-shot unsupervised 3D point cloud domain adaptation that reports 3-16% accuracy gains on PointDA-10 and GraspNetPC-10.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2601.09448","ref_index":41,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"One Prompt, Many Sounds: Modeling Listener Variability in LLM-Based Equalization","primary_cat":"cs.SD","submitted_at":"2026-01-14T12:51:36+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"LLMs using in-context learning and fine-tuning on listener experiment data generate equalization settings that align better with population preferences than random sampling or static presets.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2512.12677","ref_index":6,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Fine-Tuning Causal LLMs for Text Classification: Embedding-Based vs. Instruction-Based Approaches","primary_cat":"cs.CL","submitted_at":"2025-12-14T13:02:06+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":"2512.02764","ref_index":42,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"PEFT-Factory: Unified Parameter-Efficient Fine-Tuning of Autoregressive Large Language Models","primary_cat":"cs.CL","submitted_at":"2025-12-02T13:44:41+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"PEFT-Factory supplies a ready-to-use, extensible codebase that unifies 19 PEFT methods and evaluation pipelines for fine-tuning large autoregressive language models.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2511.21285","ref_index":32,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"PEFT-Bench: A Parameter-Efficient Fine-Tuning Methods Benchmark","primary_cat":"cs.CL","submitted_at":"2025-11-26T11:18:06+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"PEFT-Bench is a standardized end-to-end benchmark for 7 PEFT methods across 27 NLP datasets on autoregressive LLMs, accompanied by the PSCP metric that penalizes based on trainable parameters, inference speed, and training memory.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2511.11362","ref_index":5,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"On-Device Fine-Tuning via Backprop-Free Zeroth-Order Optimization","primary_cat":"cs.LG","submitted_at":"2025-11-14T14:46:29+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"MeZO enables larger models for on-device fine-tuning by estimating gradients via forward passes only, with theoretical size estimates and numerical results showing accuracy benefits when wall-clock time is sufficient.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2509.03740","ref_index":45,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"CLIP-SVD: Efficient and Interpretable Vision-Language Adaptation via Singular Values","primary_cat":"cs.CV","submitted_at":"2025-09-03T22:00:23+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"CLIP-SVD performs parameter-efficient adaptation of CLIP by fine-tuning singular values from SVD of weight matrices, reporting SOTA few-shot accuracy on 21 datasets plus a language-based interpretability analysis.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2410.18856","ref_index":12,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Entry-level guide to the use of large language models for medical research","primary_cat":"cs.AI","submitted_at":"2024-10-24T15:41:56+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":2.0,"formal_verification":"none","one_line_summary":"A tutorial guide outlining phases for integrating LLMs into medical research, including task formulation, model choice, prompt engineering, fine-tuning, and deployment with ethical considerations.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2406.00515","ref_index":156,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"A Survey on Large Language Models for Code Generation","primary_cat":"cs.CL","submitted_at":"2024-06-01T17:48:15+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"A systematic literature review that organizes recent work on LLMs for code generation into a taxonomy covering data curation, model advances, evaluations, ethics, environmental impact, and applications, with benchmark comparisons.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Augmented (Sec. 5.8) HGNN[166], REDCODER[205], ReACC[171], DocPrompting[330] RepoCoder[309], Su et al.[242] Autonomous Coding Agents (Sec. 5.9) AgentCoder [104], MetaGPT[100], CodeAct [265], AutoCodeRover [316], Devin[61] OpenDevin[199], SWE-agent[124], L2MAC[98], OpenDevin CodeAct 1.0[287] Evaluation (Sec. 5.10) Metrics Exact Match, BLEU[203], ROUGE[156], METEOR[23], CodeBLEU[221], pass@k[48] n@k[151], test case average[95], execution accuracy[218], pass@t[195], perplexity[116] Human Evaluation CodePlan[22], RepoFusion[239], CodeBLEU[221] LLM-as-a-Judge AlpacaEval[148], MT-bench[320], ICE-Score[332] Code LLMs Alignment (Sec. 5.10.3) Green[235, 277], Responsibility[168, 292], Efficiency[293], Safety[8, 9, 77, 91, 231, 294, 302], Trustworthiness[120, 202]"}],"limit":50,"offset":0}