{"total":12,"items":[{"citing_arxiv_id":"2606.08810","ref_index":39,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Continuous Language Diffusion as a Decoder-Interface Problem","primary_cat":"cs.CL","submitted_at":"2026-06-07T20:00:33+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Continuous language diffusion works by entering high-margin decoder basins where frozen T5 embeddings recover 93-96% of native decisions and linear readouts reach 97.9% agreement, implying models should be evaluated as representation-decoder systems.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.07193","ref_index":50,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Coupling Models for One-Step Discrete Generation","primary_cat":"cs.LG","submitted_at":"2026-05-08T03:40:39+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Coupling Models enable single-step discrete sequence generation via learned couplings to Gaussian latents and outperform prior one-step baselines on text perplexity, biological FBD, and image FID metrics.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2510.18165","ref_index":17,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Saber: An Efficient Sampling with Adaptive Acceleration and Backtracking Enhanced Remasking for Diffusion Language Model","primary_cat":"cs.AI","submitted_at":"2025-10-20T23:38:12+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Saber improves both speed and accuracy of diffusion language models on code generation by dynamically adjusting unmasking steps and reverting low-confidence tokens via backtracking.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2511.20657","ref_index":78,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Intelligent Agents with Emotional Intelligence: Current Trends, Challenges, and Future Prospects","primary_cat":"cs.HC","submitted_at":"2025-10-11T07:40:36+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":2.0,"formal_verification":"none","one_line_summary":"A holistic survey of affective computing for intelligent agents covering emotion understanding via multimodal data, affective cognition, emotional expression synthesis, key challenges, and future directions emphasizing generative technologies.","context_count":1,"top_context_role":"method","top_context_polarity":"use_method","context_text":"additional complexity, necessitating advanced frameworks that merge linguistic and psychological theories with machine learning techniques [69]. The absence of non-verbal cues in text poses another layer of difficulty, often leading to misinterpretations, especially among non-native speakers. Diffusion and flow-based models are also at the forefront of generating nuanced emotional text. Diffusion models, such as Diffusion-LM [78], iteratively transform noise into structured data, allowing for precise emotional control. Flow-based mod- els use invertible transformations for high-dimensional data generation, capturing emotional nuances while maintaining linguistic quality. These models can integrate affective parameters, enhancing the expressiveness of conversational language [53]."},{"citing_arxiv_id":"2507.15753","ref_index":48,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Algebraic Language Models for Inverse Design of Metamaterials via Diffusion Transformers","primary_cat":"cs.CE","submitted_at":"2025-07-21T16:09:26+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"DiffuMeta uses diffusion transformers and algebraic language representations to generate diverse 3D shell metamaterials with targeted stress-strain responses under large deformations including buckling and contact.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2411.16821","ref_index":15,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Logit-KL Flow Matching: Non-Autoregressive Text Generation via Sampling-Hybrid Inference","primary_cat":"cs.CL","submitted_at":"2024-11-25T17:15:41+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Logit-KL Flow Matching recovers the flow-matching velocity field from conditional likelihood maximization and uses iterative denoise-re-noise sampling to improve perplexity and downstream metrics over prior NAR baselines on text and code tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2408.11039","ref_index":13,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model","primary_cat":"cs.AI","submitted_at":"2024-08-20T17:48:20+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A single transformer combines language modeling loss and diffusion loss on mixed-modality data, scaling to 7B parameters and 2T tokens while matching specialized language and diffusion models.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2211.15089","ref_index":55,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Continuous diffusion for categorical data","primary_cat":"cs.CL","submitted_at":"2022-11-28T06:08:54+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"The paper proposes CDCD, a continuous-time and continuous-space diffusion framework for categorical data, and reports results on language modeling tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2211.01324","ref_index":41,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers","primary_cat":"cs.CV","submitted_at":"2022-11-02T17:43:04+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"An ensemble of stage-specialized text-to-image diffusion models improves prompt alignment over single shared-parameter models while preserving visual quality and inference speed.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"deep generative models that generate samples through an iterative denoising process. These models are trained with denoising score matching [31, 79] objectives at different noise levels and thus are also known as noise-conditioned score networks [71, 72]. They have driven successful appli- cations such as text-to-image generation [57, 59, 63], natural language generation [41], time series prediction [76], audio synthesis [39], 3D shape generation [49, 87, 91], molecu- lar conformation generation [84], protein structure genera- tion [83], machine learning security [52], and differentially private image synthesis [14]. Text-to-image diffusion models Some of the most high- quality text-to-image generative models are based on dif-"},{"citing_arxiv_id":"2210.08933","ref_index":6,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models","primary_cat":"cs.CL","submitted_at":"2022-10-17T10:49:08+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":7.0,"formal_verification":"none","one_line_summary":"DiffuSeq adapts diffusion models to conditional sequence-to-sequence text generation and reports performance matching or exceeding strong baselines including pretrained language model systems while generating more diverse outputs.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2209.14577","ref_index":2,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Rectified Flow: A Marginal Preserving Approach to Optimal Transport","primary_cat":"stat.ML","submitted_at":"2022-09-29T06:37:26+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A single-objective rectified flow variant uses neural ODEs trained by regression to monotonically decrease a fixed convex transport cost while preserving marginal distributions.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"For a given coupling (X0, X 1) of π0 and π1, the rectified flow induced by (X0, X 1) is the time-differentiable process Z = {Zt : t ∈ [0, 1]} over an artificial notion of time t ∈ [0, 1], that solves the following ordinary differential equation (ODE): dZt = vX t (Zt)dt, t ∈ [0, 1], starting from Z0 = X0, (2) where vX : Rd × [0, 1] → Rd is a time-dependent velocity field defined as the solution of inf v ∫ 1 0 E [ ∥X1 − X0 − v(Xt, t )∥2 ] dt, X t = tX1 + (1 − t)X0, (3) and Xt is the linear interpolation between X0 and X1. Eq ( 3) is a least squares regression problem of predicting the line direction of (X1 − X0) from every space-time point (Xt, t ) on the linear interpolation path, yielding a solution of vX t (z) = E [X1 − X0 |Xt = z] , which is the average of direction (X1 − X0) for all lines that pass point Xt = z at time t."},{"citing_arxiv_id":"2209.03003","ref_index":41,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","primary_cat":"cs.LG","submitted_at":"2022-09-07T08:59:55+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":8.0,"formal_verification":"none","one_line_summary":"Rectified flow learns straight-path neural ODEs for distribution transport, yielding efficient generative models and domain transfers that work well even with a single simulation step.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"have been found outperforming GANs in image synthesis in both quality and diversity [12]. Notably, thanks to the stable and scalable optimization-based training procedure, the diffusion models have successfully used in huge text-to-image generation models with astonishing results [e.g., 53, 61, 64]. It has been quickly popularized in other domains, such as video [e.g., 24, 92, 21], music [51], audio [e.g., 33, 40, 60], and text [41, 88], and more tasks such as image editing [97, 50]. A growing literature has been developed for improving the inference speed of denoising diffusion models, an example of which is the PF-ODEs/DDIM approach which gains speedup by turning SDEs into ODEs. We provide below some examples of recent works, which is by no mean exhaustive. • Improved training and inference."}],"limit":50,"offset":0}