{"total":19,"items":[{"citing_arxiv_id":"2605.31246","ref_index":46,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"BadBone: Backdoor Attacks Against Backbone Models in Visual Prompt Learning","primary_cat":"cs.CR","submitted_at":"2026-05-29T12:46:15+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"BadBone backdoors backbone models with bi-level optimization to make prompt learning on downstream tasks vulnerable while preserving model utility.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.04058","ref_index":22,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"MP-ISMoE: Mixed-Precision Interactive Side Mixture-of-Experts for Efficient Transfer Learning","primary_cat":"cs.LG","submitted_at":"2026-04-10T08:00:28+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"MP-ISMoE uses Gaussian noise perturbed iterative quantization and interactive side mixture-of-experts to deliver higher accuracy than prior memory-efficient transfer learning methods while keeping similar parameter and memory usage.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.05732","ref_index":22,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Graph Topology Information Enhanced Heterogeneous Graph Representation Learning","primary_cat":"cs.LG","submitted_at":"2026-04-07T11:35:45+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"ToGRL learns high-quality graph structures from raw heterogeneous graphs via a two-stage topology extraction process and prompt tuning, outperforming prior methods on five datasets.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2507.03724","ref_index":26,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"MemOS: A Memory OS for AI System","primary_cat":"cs.CL","submitted_at":"2025-07-04T17:21:46+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"MemOS introduces a unified memory management framework for LLMs using MemCubes to handle and evolve different memory types for improved controllability and evolvability.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"help models automatically associate contextual information during text generation. Memory&Reasoning [74] 6 T able 1Classification of Memory Types, Mechanisms, and Example References Timescale Consciousness Mechanism Example References Short-term Explicit Prompt-Based Context GPT-2 [22], GPT-3 [ 23], Prefix-Tuning [ 24], Prompt-Tuning [25], P-Tuning [26, 27], InstructGPT [28] Implicit Key-Value Cache Mechanism vLLM [ 29], StreamingLLM[ 30], H2O[ 31], LESS [ 32], KVQuant [33], RetrievalAttention [34], Memory 3 [1] Hidden State Steering Steer [ 35], ICV [ 36], ActAdd [ 37], StyleVec [38], CAA [ 39], FreeCtrl [40], EasyEdit2 [41] Activation Circuit Modula- tion SAC [42], DESTEIN [43], LM-Steer [44] Long-term"},{"citing_arxiv_id":"2502.18864","ref_index":158,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Towards an AI co-scientist","primary_cat":"cs.AI","submitted_at":"2025-02-26T06:17:13+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A multi-agent AI system generates novel biomedical hypotheses that show promising experimental validation in drug repurposing for leukemia, new targets for liver fibrosis, and a bacterial gene transfer mechanism.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2403.14608","ref_index":45,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","primary_cat":"cs.LG","submitted_at":"2024-03-21T17:55:50+00:00","verdict":"ACCEPT","verdict_confidence":"MODERATE","novelty_score":4.0,"formal_verification":"none","one_line_summary":"A comprehensive survey of PEFT algorithms for large models, covering their performance, overhead, applications, and real-world system implementations.","context_count":1,"top_context_role":"method","top_context_polarity":"background","context_text":"Fine-tuning Adapter-based Fine-tuning Adapter Design Serial Adapter [31], Parallel Adapter [32], CIAT [33], CoDA [34] Multi-task Adaptation AdapterFusion [35], AdaMix [36], PHA [37], AdapterSoup [38], MerA [39], Hyperformer [40] Soft Prompt-based Fine-tuning Soft Prompt Design Prefix-tuning [41], Prefix-Propagation [42], p-tuning v2 [43], APT [44], p-tuning [45], prompt-tuning [46], Xprompt [47], IDPG [48], LPT [49], SPT [50], APrompt [51] Training Speedup SPoT [52], TPT [53], InfoPrompt [54], PTP [55], IPT [56], SMoP [57], DePT [58] Others (IA)3 [59], MoV [60], SSF [61], IPA [62] Selective Fine-tuning Unstructural Masking U-Diff pruning [63], U-BitFit [64], PaFi [65], FishMask [66], Fish-Dip [67], LT-SFT [68], SAM [69], Child-tuning [70]"},{"citing_arxiv_id":"2309.08532","ref_index":110,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers","primary_cat":"cs.CL","submitted_at":"2023-09-15T16:50:09+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"EvoPrompt uses LLMs to run evolutionary operators on populations of prompts, outperforming human-engineered prompts by up to 25% on BIG-Bench Hard tasks across 31 datasets.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2309.03409","ref_index":18,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Large Language Models as Optimizers","primary_cat":"cs.LG","submitted_at":"2023-09-07T00:07:15+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Large language models can optimize by being prompted with histories of past solutions and scores to propose better ones, producing prompts that raise accuracy up to 8% on GSM8K and 50% on Big-Bench Hard over human-designed baselines.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2307.06435","ref_index":247,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"A Comprehensive Overview of Large Language Models","primary_cat":"cs.CL","submitted_at":"2023-07-12T20:01:52+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":2.0,"formal_verification":"none","one_line_summary":"A survey paper providing an overview of Large Language Models, their background, and recent advances in the field.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"tation (LoRA) [250] learns low-rank decomposed matrices to freeze original weights. The learned weights are fused with the original weights for inference, avoiding latency. Prompt Tuning: Prompting is an e ffective way to adapt a pre-trained LLM for the downstream task. However, manual prompts bring uncertainty in the model's prediction, where a change in a single word drops the performance [247]. Prompt tuning alleviates this problem by fine-tuning only 0.001%-3% additional parameters [251]. It concatenates trainable prompt parameters with the model embeddings [247, 40, 251]. Task- specific fixed discrete prompts are concatenated with input em- beddings in [40]. As discrete prompts bring instability, prompts are encoded through a learnable mapping in P-Tuning [247],"},{"citing_arxiv_id":"2305.14233","ref_index":165,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Enhancing Chat Language Models by Scaling High-quality Instructional Conversations","primary_cat":"cs.CL","submitted_at":"2023-05-23T16:49:14+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"UltraChat supplies 1.5 million high-quality multi-turn dialogues that, when used to fine-tune LLaMA, produce UltraLLaMA, which outperforms prior open-source chat models including Vicuna.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2305.09617","ref_index":76,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Towards Expert-Level Medical Question Answering with Large Language Models","primary_cat":"cs.CL","submitted_at":"2023-05-16T17:11:29+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Med-PaLM 2 achieves 86.5% accuracy on MedQA and approaches or exceeds prior state-of-the-art on other medical QA benchmarks while receiving higher physician preference ratings than human answers on consumer questions.","context_count":1,"top_context_role":"other","top_context_polarity":"unclear","context_text":"Table 6| Med-PaLM 2 performance on multiple-choice questions with and without overlap.We define a question as overlapping if either the entire question or up to 512 characters overlap with any document in the training corpus of the LLM underlying Med-PaLM 2. Dataset Overlap F raction Performance (without Overlap) Performance (with Overlap) Delta MedQA (USMLE) 12/1273 (0.9%) 85.3 [83.4, 87.3] 91.7 [76.0, 100.0] -6.3 [-13.5, 20.8] PubMedQA 6/500 (1.2%) 74.1 [70.2, 78.0] 66.7 [28.9, 100.0] 7.4 [-16.6, 44.3] MedMCQA 893/4183 (21.4%) 70.5 [68.9, 72.0] 75.0 [72.2, 77.9] -4.6 [-7.7, -1.3] MMLU Clinical knowledge 55/265 (20.8%) 88.6 [84.3, 92.9] 87.3 [78.5, 96.1] 1.3 [-6.8, 13.2] MMLU Medical genetics 48/100 (48.0%) 92.3 [85.1, 99.6] 91.7 [83.8, 99.5] 0.6 [-11."},{"citing_arxiv_id":"2305.07922","ref_index":20,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"CodeT5+: Open Code Large Language Models for Code Understanding and Generation","primary_cat":"cs.CL","submitted_at":"2023-05-13T14:23:07+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"CodeT5+ is a flexible encoder-decoder LLM family for code pretrained with diverse objectives on multilingual corpora and initialized from existing LLMs, achieving state-of-the-art results on code generation, completion, math programming, and retrieval tasks including new SoTA on HumanEval with the 1","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2303.16199","ref_index":55,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention","primary_cat":"cs.CV","submitted_at":"2023-03-28T17:59:12+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"LLaMA-Adapter turns frozen LLaMA 7B into a capable instruction follower using only 1.2M new parameters and zero-init attention, matching Alpaca while extending to image-conditioned reasoning on ScienceQA and COCO.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2211.16327","ref_index":45,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"On the Power of Foundation Models","primary_cat":"cs.AI","submitted_at":"2022-11-29T16:10:11+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Category theory proves prompt-based learning on perfect foundation models works only for representable tasks, fine-tuning solves tasks in the pretext category, and models can represent unseen target-category objects using source-category structure.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2205.01068","ref_index":133,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"OPT: Open Pre-trained Transformer Language Models","primary_cat":"cs.CL","submitted_at":"2022-05-02T17:49:50+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"OPT releases open decoder-only transformers up to 175B parameters that match GPT-3 performance at one-seventh the carbon cost, along with code and training logs.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2202.12837","ref_index":119,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?","primary_cat":"cs.CL","submitted_at":"2022-02-25T17:25:19+00:00","verdict":"ACCEPT","verdict_confidence":"MODERATE","novelty_score":8.0,"formal_verification":"none","one_line_summary":"Randomly replacing labels in in-context demonstrations barely hurts performance, showing that label space, input distribution, and sequence format drive in-context learning more than ground-truth labels.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2106.09685","ref_index":34,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"LoRA: Low-Rank Adaptation of Large Language Models","primary_cat":"cs.CL","submitted_at":"2021-06-17T17:37:18+00:00","verdict":"ACCEPT","verdict_confidence":"HIGH","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Adapting large language models by training only a low-rank decomposition BA added to frozen weight matrices matches full fine-tuning while cutting trainable parameters by orders of magnitude and adding no inference latency.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2104.08773","ref_index":18,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","primary_cat":"cs.CL","submitted_at":"2021-04-18T08:44:56+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Presents the NATURAL INSTRUCTIONS meta-dataset and shows generative pre-trained language models achieve 19% better generalization to unseen tasks when using task instructions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2104.08691","ref_index":30,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"The Power of Scale for Parameter-Efficient Prompt Tuning","primary_cat":"cs.CL","submitted_at":"2021-04-18T03:19:26+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Prompt tuning matches full model tuning performance on large language models while tuning only a small fraction of parameters and improves robustness to domain shifts.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}