{"total":30,"items":[{"citing_arxiv_id":"2607.01775","ref_index":34,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"Set Diffusion: Interpolating Token Orderings Between Autoregression and Diffusion for Fast and Flexible Decoding","primary_cat":"cs.LG","submitted_at":"2026-07-02T06:45:43+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Set diffusion factorizes likelihood over arbitrary token sets and uses a set-causal diffusion architecture to support KV caching and any-order decoding, yielding improved speed-quality tradeoffs versus prior diffusion LMs.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.24564","ref_index":90,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"PatternGSL: A Structured Specification Language for Template-Free and Simulation-Ready 3D Garments","primary_cat":"cs.CV","submitted_at":"2026-06-23T13:32:04+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"PatternGSL introduces a learnable specification language for sewing patterns that lets vision-language models reconstruct explicit, simulation-ready 3D garments from single images, backed by a new 300K paired dataset.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.17458","ref_index":36,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"ClaHF: A Human Feedback-inspired Reinforcement Learning Framework for Improving Classification Tasks","primary_cat":"cs.LG","submitted_at":"2026-05-17T14:00:01+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"ClaHF converts instance labels into preference signals via candidate predictions and a reward model, then applies RL optimization to improve text classification accuracy and calibration.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.16984","ref_index":42,"ref_count":2,"confidence":0.35,"is_internal_anchor":false,"paper_title":"Closing the Gap at CRAC 2026: Two-Stage Adaptation for LLM-Based Multilingual Coreference Resolution","primary_cat":"cs.CL","submitted_at":"2026-05-16T13:07:07+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Two-stage multilingual then dataset-specific adapter fine-tuning of Gemma-3-27b with headword XML mention representation and iterative annotation achieved first place in the CRAC 2026 LLM track.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.14521","ref_index":90,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"Enjoy Your Layer Normalization with the Computational Efficiency of RMSNorm","primary_cat":"cs.LG","submitted_at":"2026-05-14T08:05:39+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A framework to identify and convert foldable layer normalizations to RMSNorm for exact equivalence and faster inference in deep neural networks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.14270","ref_index":53,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"Diagnosing and Correcting Concept Omission in Multimodal Diffusion Transformers","primary_cat":"cs.CV","submitted_at":"2026-05-14T02:14:09+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Text embeddings in MM-DiTs encode a detectable omission signal for missing concepts; amplifying it via OSI reduces concept omission in text-to-image outputs on FLUX.1-Dev and SD3.5-Medium.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.14075","ref_index":57,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"Rethinking Layer Relevance in Large Language Models Beyond Cosine Similarity","primary_cat":"cs.LG","submitted_at":"2026-05-13T19:51:25+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Cosine similarity poorly predicts performance degradation from layer removal in LLMs, making direct accuracy-drop ablation a more reliable relevance metric.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.11964","ref_index":35,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"Enhancing Target-Guided Proactive Dialogue Systems via Conversational Scenario Modeling and Intent-Keyword Bridging","primary_cat":"cs.CL","submitted_at":"2026-05-12T11:18:45+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Conversational scenario modeling from user profiles and domain knowledge, combined with intent-keyword bridging, improves proactivity, fluency, and informativeness in target-guided proactive dialogue systems.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.10640","ref_index":84,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"Towards Understanding Continual Factual Knowledge Acquisition of Language Models: From Theory to Algorithm","primary_cat":"cs.CL","submitted_at":"2026-05-11T14:28:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Theoretical analysis of continual factual knowledge acquisition shows data replay stabilizes pretrained knowledge by shifting convergence dynamics while regularization only slows forgetting, leading to the STOC method for attention-based replay selection.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.16384","ref_index":9,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"Mutual Enhancement Between Global Tokens and Patch Tokens: From Theory to Practice","primary_cat":"cs.CV","submitted_at":"2026-05-11T10:51:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"TaTok is a theoretically grounded adaptive tokenization method that uses global tokens and cumulative conditional entropy filtering to reduce redundancy while improving reconstruction quality over fixed-rate patch tokenization.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.10129","ref_index":7,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"Synthetic Pre-Pre-Training Improves Language Model Robustness to Noisy Pre-Training Data","primary_cat":"cs.CL","submitted_at":"2026-05-11T07:40:39+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Synthetic pre-pre-training on structured data improves LLM robustness to noisy pre-training, matching baseline loss with up to 49% fewer natural tokens for a 1B model.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.09472","ref_index":51,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"Positional LSH: Binary Block Matrix Approximation for Attention with Linear Biases","primary_cat":"cs.LG","submitted_at":"2026-05-10T10:58:20+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"ALiBi bias is the expectation of positional LSH-induced block masks, yielding spectral and max-norm approximation bounds that reduce long-context biased attention to randomized short-context unbiased attention.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.05902","ref_index":62,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"Evaluating Non-English Developer Support in Machine Learning for Software Engineering","primary_cat":"cs.SE","submitted_at":"2026-05-07T09:14:46+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Code LLMs generate substantially worse comments outside English, and no tested automatic metric or LLM judge reliably matches human assessment of those outputs.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.05365","ref_index":71,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"ZAYA1-8B Technical Report","primary_cat":"cs.AI","submitted_at":"2026-05-06T18:44:08+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"ZAYA1-8B is a reasoning MoE model with 700M active parameters that matches larger models on math and coding benchmarks and reaches 91.9% on AIME'25 via Markovian RSA test-time compute.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.04762","ref_index":4,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"TCRTransBench: A Comprehensive Benchmark for Bidirectional TCR-Peptide Sequence Generation","primary_cat":"q-bio.CB","submitted_at":"2026-05-06T11:09:19+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"TCRTransBench provides a new benchmark with bidirectional TCR-peptide generation tasks, a large validated dataset, and metrics to evaluate neural models for immunological sequence modeling.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.04449","ref_index":47,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"GEM: Graph-Enhanced Mixture-of-Experts with ReAct Agents for Dialogue State Tracking","primary_cat":"cs.CL","submitted_at":"2026-05-06T03:25:04+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"GEM achieves 65.19% joint goal accuracy on MultiWOZ 2.2 by routing between a graph neural network expert for dialogue structure and a T5 expert for sequences, plus ReAct agents for value generation, outperforming prior SOTA methods.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.01399","ref_index":40,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"Verbal-R3: Verbal Reranker as the Missing Bridge between Retrieval and Reasoning","primary_cat":"cs.CL","submitted_at":"2026-05-02T11:43:23+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Verbal-R3 uses a verbal reranker to generate analytic narratives that guide retrieval and reasoning in LLMs, achieving SOTA results on complex QA benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.01167","ref_index":40,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"Minimizing Collateral Damage in Activation Steering","primary_cat":"cs.LG","submitted_at":"2026-05-01T23:52:54+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Activation steering is cast as constrained optimization that minimizes collateral damage by weighting perturbations according to the empirical second-moment matrix of activations instead of assuming isotropy.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.00348","ref_index":53,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"Block-wise Codeword Embedding for Reliable Multi-bit Text Watermarking","primary_cat":"cs.CR","submitted_at":"2026-05-01T02:14:38+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"BREW uses block voting and window-shifting verification to reach TPR 0.965 and FPR 0.02 under 10% synonym substitution, addressing high false-positive issues in prior multi-bit LLM watermarking.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.21215","ref_index":24,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"The Recurrent Transformer: Greater Effective Depth and Efficient Decoding","primary_cat":"cs.LG","submitted_at":"2026-04-23T02:12:58+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Recurrent Transformers add per-layer recurrent memory via self-attention on own activations plus a tiling algorithm that reduces training memory traffic, yielding better C4 pretraining cross-entropy than parameter-matched standard transformers with fewer layers.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.19167","ref_index":57,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"LBLLM: Lightweight Binarization of Large Language Models via Three-Stage Distillation","primary_cat":"cs.LG","submitted_at":"2026-04-21T07:25:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"LBLLM achieves better accuracy than prior binarization methods for LLMs by decoupling weight and activation quantization through initialization, layer-wise distillation, and learnable activation scaling.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.18955","ref_index":87,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"Assessing Capabilities of Large Language Models in Social Media Analytics: A Multi-task Quest","primary_cat":"cs.CL","submitted_at":"2026-04-21T01:05:52+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"LLMs show mixed results on authorship verification, post generation, and attribute inference from Twitter data, with new frameworks and user studies establishing benchmarks for these analytics tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.18258","ref_index":39,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"Long-Text-to-Image Generation via Compositional Prompt Decomposition","primary_cat":"cs.CV","submitted_at":"2026-04-20T13:31:36+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"PRISM lets pre-trained text-to-image models handle long prompts by breaking them into compositional parts, predicting noise separately, and merging outputs via energy-based conjunction, matching fine-tuned models while generalizing better to prompts over 500 tokens.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.18124","ref_index":58,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"TLoRA: Task-aware Low Rank Adaptation of Large Language Models","primary_cat":"cs.CL","submitted_at":"2026-04-20T11:43:55+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"TLoRA jointly optimizes LoRA initialization via task-data SVD and sensitivity-driven rank allocation, delivering stronger results than standard LoRA across NLU, reasoning, math, code, and chat tasks while using fewer trainable parameters.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.17396","ref_index":158,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"Representation-Guided Parameter-Efficient LLM Unlearning","primary_cat":"cs.CL","submitted_at":"2026-04-19T11:59:58+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"REGLU guides LoRA-based unlearning via representation subspaces and orthogonal regularization to outperform prior methods on forget-retain trade-off in LLM benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2502.10248","ref_index":193,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model","primary_cat":"cs.CV","submitted_at":"2025-02-14T15:58:10+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Step-Video-T2V describes a 30B-parameter text-to-video model with custom Video-VAE, 3D DiT, flow matching, and Video-DPO that claims state-of-the-art results on a new internal benchmark.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2502.02737","ref_index":61,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model","primary_cat":"cs.CL","submitted_at":"2025-02-04T21:43:16+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"SmolLM2 is a 1.7B-parameter language model that outperforms Qwen2.5-1.5B and Llama3.2-1B after overtraining on 11 trillion tokens using custom FineMath, Stack-Edu, and SmolTalk datasets in a multi-stage pipeline.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2412.13663","ref_index":53,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference","primary_cat":"cs.CL","submitted_at":"2024-12-18T09:39:44+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"ModernBERT is a new bidirectional encoder model achieving SOTA performance on diverse classification and retrieval benchmarks while offering superior speed and memory efficiency for long-context inference.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2408.06072","ref_index":49,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","primary_cat":"cs.CV","submitted_at":"2024-08-12T11:47:11+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"CogVideoX generates coherent 10-second text-to-video outputs at high resolution using a 3D VAE, expert adaptive LayerNorm transformer, progressive training, and a custom data pipeline, claiming state-of-the-art results.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2405.17428","ref_index":108,"ref_count":1,"confidence":0.35,"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}],"limit":50,"offset":0}