{"total":12,"items":[{"citing_arxiv_id":"2606.24747","ref_index":18,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Scaling Laws for Task-Specific LLM Distillation","primary_cat":"cs.AI","submitted_at":"2026-06-23T16:09:57+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Empirical scaling laws for task-specific LLM distillation in quantitative finance indicate that chain-of-thought supervision recovers general knowledge lost during iterative pruning while in-domain performance degrades predictably.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.21322","ref_index":35,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Optimized Federated Knowledge Distillation with Distributed Neural Architecture Search","primary_cat":"cs.LG","submitted_at":"2026-05-20T15:50:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"FedKDNAS combines client-side neural architecture search with knowledge distillation from aggregated server predictions to improve accuracy and efficiency in heterogeneous federated learning.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.09356","ref_index":22,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Function-Space ADMM for Decentralized Federated Learning: A Control Theoretic Perspective","primary_cat":"cs.LG","submitted_at":"2026-05-10T06:11:46+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"FedF-ADMM uses function-space ADMM updates projected via knowledge distillation plus a PI-like stabilization term to deliver faster, more stable convergence and higher accuracy than prior decentralized FL methods under severe non-IID conditions.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Knowledge distillation-based federated learning While the above approaches synchronize model parame- ters, KD-based FL provides an alternative path by aligning model outputs rather than parameters, mitigating challenges such as high communication costs and heterogeneous model architectures [21]. Prior to its adoption in DFL, co-distillation was proposed for data-center environments [22], [23], where devices train local models and exchange shared output pre- dictions, which are averaged to form soft labels. This process can be viewed as a distributed form of KD [24]. While co- distillation was designed for data-center environments, and thus it assumes shared training data, the similar idea has been proposed for FL scenarios. Jeonget al."},{"citing_arxiv_id":"2605.05718","ref_index":17,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Enabling Federated Inference via Unsupervised Consensus Embedding","primary_cat":"cs.LG","submitted_at":"2026-05-07T06:08:06+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"CE-FI maps heterogeneous model representations to a shared embedding space via unsupervised training on unlabeled data, enabling privacy-preserving federated inference that outperforms solo models on image classification benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.23268","ref_index":25,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"LatentBurst: A Fast and Efficient Multi Frame Super-Resolution for Hexadeca-Bayer Pattern CIS images","primary_cat":"cs.CV","submitted_at":"2026-04-25T12:19:33+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"LatentBurst is a new multi-frame super-resolution network for hexadeca-Bayer CIS images that uses pyramid latent alignment, an efficient UNet, and two-step knowledge distillation to handle motion and run on mobile devices.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.21027","ref_index":178,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"HypEHR: Hyperbolic Modeling of Electronic Health Records for Efficient Question Answering","primary_cat":"cs.AI","submitted_at":"2026-04-22T19:18:36+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A 22M-parameter hyperbolic model answers structured EHR questions with accuracy close to LLM-based systems (EHRXQA 89.5%, MIMIC-Instr 76.0%).","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2507.21166","ref_index":6,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"The Ratchet Effect in Silico: How Interaction Drives Cumulative Intelligence in Large Language Models","primary_cat":"cs.LG","submitted_at":"2025-07-25T13:05:01+00:00","verdict":"REJECT","verdict_confidence":"MODERATE","novelty_score":4.0,"formal_verification":"none","one_line_summary":"POLIS gets 1-4B parameter language models to verify each other's math answers, store the good ones in shared memory, and fine-tune on them, reporting big average gains, but the protocol is underspecified.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2507.06261","ref_index":1,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","primary_cat":"cs.CL","submitted_at":"2025-07-07T17:36:04+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Gemini 2.5 Pro and Flash models are presented as achieving frontier performance in reasoning, coding, and long-context multimodal tasks while spanning a cost-capability Pareto curve.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2503.19786","ref_index":2,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Gemma 3 Technical Report","primary_cat":"cs.CL","submitted_at":"2025-03-25T15:52:34+00:00","verdict":"ACCEPT","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Gemma 3 introduces multimodal open models with architectural changes for efficient long context, trained via distillation and a new post-training recipe that makes the 4B version competitive with prior 27B models and the 27B version comparable to Gemini-1.5-Pro.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2408.00118","ref_index":159,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Gemma 2: Improving Open Language Models at a Practical Size","primary_cat":"cs.CL","submitted_at":"2024-07-31T19:13:07+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":3.0,"formal_verification":"none","one_line_summary":"Gemma 2 models achieve leading performance at their sizes by combining established Transformer modifications with knowledge distillation for the 2B and 9B variants.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2309.16588","ref_index":182,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Vision Transformers Need Registers","primary_cat":"cs.CV","submitted_at":"2023-09-28T16:45:46+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Adding register tokens to Vision Transformers eliminates high-norm background artifacts and raises state-of-the-art performance on dense visual prediction tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2104.14294","ref_index":1,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Emerging Properties in Self-Supervised Vision Transformers","primary_cat":"cs.CV","submitted_at":"2021-04-29T12:28:51+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":8.0,"formal_verification":"none","one_line_summary":"Self-supervised ViTs show emergent semantic segmentation and 78.3% k-NN accuracy on ImageNet; DINO reaches 80.1% linear evaluation with ViT-Base.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}