{"work":{"id":"48172a5a-0dfc-45cf-9fdc-988f99c16450","openalex_id":null,"doi":null,"arxiv_id":null,"raw_key":"raw:bedb6f63c7e4753715e08421","title":"Advances in neural information processing systems , volume=","authors":null,"authors_text":"Denoising diffusion probabilistic models , author=","year":null,"venue":null,"abstract":null,"external_url":null,"cited_by_count":null,"metadata_source":"raw_reference","metadata_fetched_at":"2026-07-11T02:58:01.546295+00:00","pith_arxiv_id":null,"created_at":"2026-05-10T18:26:22.395558+00:00","updated_at":"2026-07-11T02:58:01.546295+00:00","title_quality_ok":false,"display_title":"Advances in neural information processing systems , volume=","render_title":"Advances in neural information processing systems , volume="},"hub":{"state":{"work_id":"48172a5a-0dfc-45cf-9fdc-988f99c16450","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":95,"external_cited_by_count":null,"distinct_field_count":14,"first_pith_cited_at":"2024-06-06T04:22:11+00:00","last_pith_cited_at":"2026-07-09T17:59:52+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-08-22T15:49:27.524173+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":4},{"context_role":"method","n":4}],"polarity_counts":[{"context_polarity":"use_method","n":4},{"context_polarity":"background","n":2},{"context_polarity":"unclear","n":2}],"runs":{"context_extract":{"job_type":"context_extract","status":"succeeded","result":{"enqueued_papers":25},"error":null,"updated_at":"2026-05-26T01:26:34.510787+00:00"},"graph_features":{"job_type":"graph_features","status":"succeeded","result":{"co_cited":[{"title":"Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=","work_id":"575b0292-9b85-4da9-a1f5-5a4768b0f754","shared_citers":28},{"title":"Score-Based Generative Modeling through Stochastic Differential Equations","work_id":"d9110e53-a5d4-4794-a4c5-a575e91c31ad","shared_citers":22},{"title":"Denoising Diffusion Implicit Models","work_id":"8fa2128b-d18c-405c-ac92-0e669cf89ac0","shared_citers":20},{"title":"Flow Matching for Generative Modeling","work_id":"6edb71c4-5d64-40af-a394-9757ea051a36","shared_citers":17},{"title":"Advances in neural information processing systems , volume=","work_id":"a1fd09f1-b62b-4aca-a5ef-dd2b50ad08b5","shared_citers":16},{"title":"Advances in neural information processing systems , volume=","work_id":"2f872461-c98f-40a7-919b-53d4d9b3e586","shared_citers":15},{"title":"International conference on machine learning , pages=","work_id":"f2187cd6-e743-4327-931e-4fb626cf0064","shared_citers":15},{"title":"Auto-Encoding Variational Bayes","work_id":"97d95295-30e1-42b4-bbf6-85f0fa4edb44","shared_citers":14},{"title":"Classifier-Free Diffusion Guidance","work_id":"acf2c588-c088-4a6c-938e-150ad7c666d7","shared_citers":14},{"title":"Proceedings of the IEEE/CVF international conference on computer vision , pages=","work_id":"8d3af2d5-f2a3-4ce9-8358-51fef7d65c4a","shared_citers":14},{"title":"International conference on machine learning , pages=","work_id":"1031f0f0-cd67-4170-83ad-9a088b363c67","shared_citers":13},{"title":"2016 , publisher=","work_id":"cf0899e0-53ee-4591-aae4-f38fa5ac12ad","shared_citers":12},{"title":"Adam: A Method for Stochastic Optimization","work_id":"1910796d-9b52-4683-bf5c-de9632c1028b","shared_citers":12},{"title":"Decoupled Weight Decay Regularization","work_id":"07ef7360-d385-4033-83f7-8384a6325204","shared_citers":12},{"title":"Scaling Learning Algorithms Towards","work_id":"bb2761cc-98d0-411b-92f6-803773d64460","shared_citers":11},{"title":"and Osindero, Simon and Teh, Yee Whye , journal =","work_id":"0a5921e3-ac4e-46f1-85ae-866119a87be0","shared_citers":10},{"title":"Proceedings of the IEEE conference on computer vision and pattern recognition , pages=","work_id":"d68c03bf-9512-49ef-b9bd-f8b4546deae5","shared_citers":10},{"title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","work_id":"8034c587-fba6-4941-87ba-c98f2ac962cb","shared_citers":10},{"title":"2009 IEEE conference on computer vision and pattern recognition , pages=","work_id":"0287b3d7-3294-4d36-bdf0-64add6c6c84b","shared_citers":9},{"title":"Advances in neural information processing systems , volume=","work_id":"2c0209fa-a8b6-44c1-8db8-06736cd804a8","shared_citers":9},{"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","shared_citers":9},{"title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","work_id":"a1989e1b-d66d-4533-be3a-fb9c5fd62290","shared_citers":8},{"title":"Advances in neural information processing systems , volume=","work_id":"50a0d868-5d19-4d7e-991e-0974d5939eef","shared_citers":7},{"title":"Advances in neural information processing systems , volume=","work_id":"0aa0ce1a-9941-46aa-ad9b-5d1b6aed53ea","shared_citers":7}],"time_series":[{"n":5,"year":2024},{"n":67,"year":2026}],"dependency_candidates":[{"n":1,"role":"method","polarity":"use_method","paper_title":"Ada-Diffuser: Latent-Aware Adaptive Diffusion for Decision-Making","primary_cat":"cs.LG","context_text":"M=⟨S,A,Θ,T,R, γ, P Θ⟩, where S is the state space, A is the action space, and Θ is the space of task-specific latent parameters. For each θ∈Θ , the transition and reward functions are given by Tθ :S × A → P(S) and Rθ :S × A →R , respectively. The parameter θ is sampled from a prior distribution PΘ at the beginning of an episode and remains fixed during the episode. The discount factor is denoted by γ∈[0,1) . This framework defines a family of MDPs indexed by the latent parameter θ, with each θ inducing a different set of dynamics and reward functions. It can be seen as a special case of a contextual MDP where the context is latent and fixed per episode.Xie et al. (2021) 32 Published as a conference paper at ICLR 2026 further generalize this framework by allowing the task parameter θ to evolve dynamically across episodes, rather than being fixed. Bayes-Adaptive MDPs (BAMDPs) are closely related to both HiP-MDPs and contextual MDPs (CMDPs). In BAMDPs, the agent maintains a posterior distribution over MDPs based on its interaction history. Specifically, it maintains a belief bt(R, T) =p(R, T|τ :t), where τ:t = {s0,a 0, r0, . . . ,st} denotes the trajectory observed up to time t. This belief captures the agent's uncertainty about the underlying transition and reward functions. The transition and reward functions can then be defined in expectation over this posterior, effectively conditioning decision-making on the belief bt. When the environment is driven by hidden contextual variables or latent task parameters, such as in CMDPs or HiP-MDPs-this belief can be interpreted as a distribution over these latent variables. In this view, BAMDPs provide a non-parametric framework for reasoning over hidden structure, while approaches like ours explicitly model such latent variables and infer their posterior distributions using amortized inference. Both aim to enable adaptive planning and learning under uncertainty, but differ in how latent structure is represented and ","citing_arxiv_id":"2605.16054"},{"n":1,"role":"method","polarity":"use_method","paper_title":"GeoQuery: Geometry-Query Diffusion for Sparse-View Reconstruction","primary_cat":"cs.CV","context_text":"− 1 2 (x−𝜇) ⊤Σ−1 (x−𝜇) \u0013 .(1) The covariance is optimized via a factored representation Σ= RSS⊤R⊤ to ensure semi-definiteness. To render the scene, 3D Gaussians are projected into 2D image space. The final color 𝐶 of a pixel is computed by alpha-blending 𝑁 ordered Gaussians overlapping the pixel: 𝐶= 𝑁∑︁ 𝑖=1 𝑐𝑖𝛼𝑖𝐺 2𝐷 𝑖 (x) 𝑖−1Ö 𝑗=1 (1−𝛼 𝑗𝐺 2𝐷 𝑗 (x)),(2) where 𝑐𝑖, 𝛼𝑖, and𝐺 2𝐷 𝑖 (x) denote the color, opacity, and the evaluation of the𝑖-th projected 2D Gaussian at pixel positionx, respectively. 3.2 Diffusion Models Diffusion models [Ho et al. 2020; Rombach et al. 2022; Song et al. 2020] learn a data distribution 𝑝data (x) via iterative denoising. A forward process progressively perturbs data by adding Gaussian","citing_arxiv_id":"2605.12399"},{"n":1,"role":"method","polarity":"use_method","paper_title":"Polyphonia: Zero-Shot Timbre Transfer in Polyphonic Music with Acoustic-Informed Attention Calibration","primary_cat":"cs.SD","context_text":"Interpolation achieves lower entropy, reflecting a sharper distri- bution critical for precise localization. For more details of this analysis, please refer toApp. F. mtext ∈ {0,1} Ly to isolate the target entity within the prompt Ytgt. Let Itgt denote the set of token indices of the target subject (e.g., \"violin\"). The mask is defined as: mtext i = ( 1,ifi∈ I tgt 0,otherwise (12) Subsequently, a Spatio-Textual Bias MatrixB is synthesized via the outer product of g=Flatten(G)∈R Lz and the token mask mtext. This bias is injected into the pre-Softmax attention energy to regulate the attention distribution: Ebias = QK ⊤ √ d +λ·B,B=g⊗m text ∈R Lz×Ly (13) Attnmod(Q, K, V) =Softmax(E bias)V(14) where λ is a scalar controlling modulation strength.","citing_arxiv_id":"2605.10203"}]},"error":null,"updated_at":"2026-05-26T01:26:28.125803+00:00"},"identity_refresh":{"job_type":"identity_refresh","status":"succeeded","result":{"items":[{"title":"Qwen3 Technical Report","outcome":"unchanged","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","resolver":"local_arxiv","confidence":0.98,"old_work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e"}],"counts":{"fixed":0,"merged":0,"unchanged":1,"quarantined":0,"needs_external_resolution":0},"errors":[],"attempted":1},"error":null,"updated_at":"2026-05-26T01:26:27.959167+00:00"},"summary_claims":{"job_type":"summary_claims","status":"succeeded","result":{"title":"Advances in neural information processing systems , volume=","claims":[{"claim_text":"Interpolation achieves lower entropy, reflecting a sharper distri- bution critical for precise localization. For more details of this analysis, please refer toApp. F. mtext ∈ {0,1} Ly to isolate the target entity within the prompt Ytgt. Let Itgt denote the set of token indices of the target subject (e.g., \"violin\"). The mask is defined as: mtext i = ( 1,ifi∈ I tgt 0,otherwise (12) Subsequently, a Spatio-Textual Bias MatrixB is synthesized via the outer product of g=Flatten(G)∈R Lz and the token ","claim_type":"method","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"− 1 2 (x−𝜇) ⊤Σ−1 (x−𝜇) \u0013 .(1) The covariance is optimized via a factored representation Σ= RSS⊤R⊤ to ensure semi-definiteness. To render the scene, 3D Gaussians are projected into 2D image space. The final color 𝐶 of a pixel is computed by alpha-blending 𝑁 ordered Gaussians overlapping the pixel: 𝐶= 𝑁∑︁ 𝑖=1 𝑐𝑖𝛼𝑖𝐺 2𝐷 𝑖 (x) 𝑖−1Ö 𝑗=1 (1−𝛼 𝑗𝐺 2𝐷 𝑗 (x)),(2) where 𝑐𝑖, 𝛼𝑖, and𝐺 2𝐷 𝑖 (x) denote the color, opacity, and the evaluation of the𝑖-th projected 2D Gaussian at pixel positionx, respectively. 3.2 ","claim_type":"method","confidence":0.85,"evidence_strength":"citation_context"},{"claim_text":"M=⟨S,A,Θ,T,R, γ, P Θ⟩, where S is the state space, A is the action space, and Θ is the space of task-specific latent parameters. For each θ∈Θ , the transition and reward functions are given by Tθ :S × A → P(S) and Rθ :S × A →R , respectively. The parameter θ is sampled from a prior distribution PΘ at the beginning of an episode and remains fixed during the episode. The discount factor is denoted by γ∈[0,1) . This framework defines a family of MDPs indexed by the latent parameter θ, with each θ i","claim_type":"method","confidence":0.8,"evidence_strength":"citation_context"},{"claim_text":"decoder D, which takes latent tokens L from the Perceiver Resam- pler and outputs head meshes with consistent topology. Given the shared face connectivity F across all training meshes, the mesh structure naturally defines a graphG. Graph Convolution.For vertex 𝑣𝑖 with feature 𝐹𝑖 and neighbors N (𝑖), our graph convolution is defined as: 𝐹 ′ 𝑖 =𝑊 0𝐹𝑖 + Í 𝑗∈ N (𝑖) 𝑊1𝐹 𝑗,(1) , Vol. 1, No. 1, Article . Publication date: May 2026. 4•Bojun Xiong, Zoubin Bi, Xinghui Peng, Yunmu Wang, Junchen Deng, Jun L","claim_type":"background","confidence":0.6,"evidence_strength":"citation_context"},{"claim_text":"dynamics in these directions remain diffusive. Although the effective diffusion coefficientηdk turns out to be very small, the large number of these nearly-flat directions leads to a noticeable divergence of individual trajectories. In the directions with large eigenvaluesηnλi ≫1the system reaches the stationary state given by Πii n ≈ ηdi 2λi −ηλ 2 i −ηΓ ii .(39) The behavior in the other (intermediate) directions is in between these two limiting cases. We also observe empirically that, for dire","claim_type":"background","confidence":0.5,"evidence_strength":"citation_context"},{"claim_text":"t (see Section 5); for learned ¯vthe residual remains random but acts as a control variate. 4 Path-Coupled Bellman Flows for Distributional Reinforcement Learning Figure 1.The Architecture of Path-Coupled Bellman Flows (PCBF). Using this control variate, we define the PCBF training target as follows: uλ t := (R+γX ′−X0)+λ h vθ−(t, Zs′ t |s ′, a′)−(X ′ −X 0) i . (13) Setting λ= 0 recovers the baseline BCFM estimator (un- biased, high variance). Nonzero λ introduces a variance- reducing correction","claim_type":"background","confidence":0.5,"evidence_strength":"citation_context"}],"why_cited":"Pith tracks Advances in neural information processing systems , volume= because it crossed a citation-hub threshold. Current citing contexts most often use it as background evidence (4 contexts).","role_counts":[{"n":4,"context_role":"background"},{"n":3,"context_role":"method"}]},"error":null,"updated_at":"2026-05-26T01:26:27.963867+00:00"}},"summary":{"title":"Advances in neural information processing systems , volume=","claims":[{"claim_text":"Interpolation achieves lower entropy, reflecting a sharper distri- bution critical for precise localization. For more details of this analysis, please refer toApp. F. mtext ∈ {0,1} Ly to isolate the target entity within the prompt Ytgt. Let Itgt denote the set of token indices of the target subject (e.g., \"violin\"). The mask is defined as: mtext i = ( 1,ifi∈ I tgt 0,otherwise (12) Subsequently, a Spatio-Textual Bias MatrixB is synthesized via the outer product of g=Flatten(G)∈R Lz and the token ","claim_type":"method","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"− 1 2 (x−𝜇) ⊤Σ−1 (x−𝜇) \u0013 .(1) The covariance is optimized via a factored representation Σ= RSS⊤R⊤ to ensure semi-definiteness. To render the scene, 3D Gaussians are projected into 2D image space. The final color 𝐶 of a pixel is computed by alpha-blending 𝑁 ordered Gaussians overlapping the pixel: 𝐶= 𝑁∑︁ 𝑖=1 𝑐𝑖𝛼𝑖𝐺 2𝐷 𝑖 (x) 𝑖−1Ö 𝑗=1 (1−𝛼 𝑗𝐺 2𝐷 𝑗 (x)),(2) where 𝑐𝑖, 𝛼𝑖, and𝐺 2𝐷 𝑖 (x) denote the color, opacity, and the evaluation of the𝑖-th projected 2D Gaussian at pixel positionx, respectively. 3.2 ","claim_type":"method","confidence":0.85,"evidence_strength":"citation_context"},{"claim_text":"M=⟨S,A,Θ,T,R, γ, P Θ⟩, where S is the state space, A is the action space, and Θ is the space of task-specific latent parameters. For each θ∈Θ , the transition and reward functions are given by Tθ :S × A → P(S) and Rθ :S × A →R , respectively. The parameter θ is sampled from a prior distribution PΘ at the beginning of an episode and remains fixed during the episode. The discount factor is denoted by γ∈[0,1) . This framework defines a family of MDPs indexed by the latent parameter θ, with each θ i","claim_type":"method","confidence":0.8,"evidence_strength":"citation_context"},{"claim_text":"decoder D, which takes latent tokens L from the Perceiver Resam- pler and outputs head meshes with consistent topology. Given the shared face connectivity F across all training meshes, the mesh structure naturally defines a graphG. Graph Convolution.For vertex 𝑣𝑖 with feature 𝐹𝑖 and neighbors N (𝑖), our graph convolution is defined as: 𝐹 ′ 𝑖 =𝑊 0𝐹𝑖 + Í 𝑗∈ N (𝑖) 𝑊1𝐹 𝑗,(1) , Vol. 1, No. 1, Article . Publication date: May 2026. 4•Bojun Xiong, Zoubin Bi, Xinghui Peng, Yunmu Wang, Junchen Deng, Jun L","claim_type":"background","confidence":0.6,"evidence_strength":"citation_context"},{"claim_text":"dynamics in these directions remain diffusive. Although the effective diffusion coefficientηdk turns out to be very small, the large number of these nearly-flat directions leads to a noticeable divergence of individual trajectories. In the directions with large eigenvaluesηnλi ≫1the system reaches the stationary state given by Πii n ≈ ηdi 2λi −ηλ 2 i −ηΓ ii .(39) The behavior in the other (intermediate) directions is in between these two limiting cases. We also observe empirically that, for dire","claim_type":"background","confidence":0.5,"evidence_strength":"citation_context"},{"claim_text":"t (see Section 5); for learned ¯vthe residual remains random but acts as a control variate. 4 Path-Coupled Bellman Flows for Distributional Reinforcement Learning Figure 1.The Architecture of Path-Coupled Bellman Flows (PCBF). Using this control variate, we define the PCBF training target as follows: uλ t := (R+γX ′−X0)+λ h vθ−(t, Zs′ t |s ′, a′)−(X ′ −X 0) i . (13) Setting λ= 0 recovers the baseline BCFM estimator (un- biased, high variance). Nonzero λ introduces a variance- reducing correction","claim_type":"background","confidence":0.5,"evidence_strength":"citation_context"}],"why_cited":"Pith tracks Advances in neural information processing systems , volume= because it crossed a citation-hub threshold. Current citing contexts most often use it as background evidence (4 contexts).","role_counts":[{"n":4,"context_role":"background"},{"n":3,"context_role":"method"}]},"graph":{"co_cited":[{"title":"Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=","work_id":"575b0292-9b85-4da9-a1f5-5a4768b0f754","shared_citers":28},{"title":"Score-Based Generative Modeling through Stochastic Differential Equations","work_id":"d9110e53-a5d4-4794-a4c5-a575e91c31ad","shared_citers":22},{"title":"Denoising Diffusion Implicit Models","work_id":"8fa2128b-d18c-405c-ac92-0e669cf89ac0","shared_citers":20},{"title":"Flow Matching for Generative Modeling","work_id":"6edb71c4-5d64-40af-a394-9757ea051a36","shared_citers":17},{"title":"Advances in neural information processing systems , volume=","work_id":"a1fd09f1-b62b-4aca-a5ef-dd2b50ad08b5","shared_citers":16},{"title":"Advances in neural information processing systems , volume=","work_id":"2f872461-c98f-40a7-919b-53d4d9b3e586","shared_citers":15},{"title":"International conference on machine learning , pages=","work_id":"f2187cd6-e743-4327-931e-4fb626cf0064","shared_citers":15},{"title":"Auto-Encoding Variational Bayes","work_id":"97d95295-30e1-42b4-bbf6-85f0fa4edb44","shared_citers":14},{"title":"Classifier-Free Diffusion Guidance","work_id":"acf2c588-c088-4a6c-938e-150ad7c666d7","shared_citers":14},{"title":"Proceedings of the IEEE/CVF international conference on computer vision , pages=","work_id":"8d3af2d5-f2a3-4ce9-8358-51fef7d65c4a","shared_citers":14},{"title":"International conference on machine learning , pages=","work_id":"1031f0f0-cd67-4170-83ad-9a088b363c67","shared_citers":13},{"title":"2016 , publisher=","work_id":"cf0899e0-53ee-4591-aae4-f38fa5ac12ad","shared_citers":12},{"title":"Adam: A Method for Stochastic Optimization","work_id":"1910796d-9b52-4683-bf5c-de9632c1028b","shared_citers":12},{"title":"Decoupled Weight Decay Regularization","work_id":"07ef7360-d385-4033-83f7-8384a6325204","shared_citers":12},{"title":"Scaling Learning Algorithms Towards","work_id":"bb2761cc-98d0-411b-92f6-803773d64460","shared_citers":11},{"title":"and Osindero, Simon and Teh, Yee Whye , journal =","work_id":"0a5921e3-ac4e-46f1-85ae-866119a87be0","shared_citers":10},{"title":"Proceedings of the IEEE conference on computer vision and pattern recognition , pages=","work_id":"d68c03bf-9512-49ef-b9bd-f8b4546deae5","shared_citers":10},{"title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","work_id":"8034c587-fba6-4941-87ba-c98f2ac962cb","shared_citers":10},{"title":"2009 IEEE conference on computer vision and pattern recognition , pages=","work_id":"0287b3d7-3294-4d36-bdf0-64add6c6c84b","shared_citers":9},{"title":"Advances in neural information processing systems , volume=","work_id":"2c0209fa-a8b6-44c1-8db8-06736cd804a8","shared_citers":9},{"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","shared_citers":9},{"title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","work_id":"a1989e1b-d66d-4533-be3a-fb9c5fd62290","shared_citers":8},{"title":"Advances in neural information processing systems , volume=","work_id":"50a0d868-5d19-4d7e-991e-0974d5939eef","shared_citers":7},{"title":"Advances in neural information processing systems , volume=","work_id":"0aa0ce1a-9941-46aa-ad9b-5d1b6aed53ea","shared_citers":7}],"time_series":[{"n":5,"year":2024},{"n":67,"year":2026}],"dependency_candidates":[{"n":1,"role":"method","polarity":"use_method","paper_title":"Ada-Diffuser: Latent-Aware Adaptive Diffusion for Decision-Making","primary_cat":"cs.LG","context_text":"M=⟨S,A,Θ,T,R, γ, P Θ⟩, where S is the state space, A is the action space, and Θ is the space of task-specific latent parameters. For each θ∈Θ , the transition and reward functions are given by Tθ :S × A → P(S) and Rθ :S × A →R , respectively. The parameter θ is sampled from a prior distribution PΘ at the beginning of an episode and remains fixed during the episode. The discount factor is denoted by γ∈[0,1) . This framework defines a family of MDPs indexed by the latent parameter θ, with each θ inducing a different set of dynamics and reward functions. It can be seen as a special case of a contextual MDP where the context is latent and fixed per episode.Xie et al. (2021) 32 Published as a conference paper at ICLR 2026 further generalize this framework by allowing the task parameter θ to evolve dynamically across episodes, rather than being fixed. Bayes-Adaptive MDPs (BAMDPs) are closely related to both HiP-MDPs and contextual MDPs (CMDPs). In BAMDPs, the agent maintains a posterior distribution over MDPs based on its interaction history. Specifically, it maintains a belief bt(R, T) =p(R, T|τ :t), where τ:t = {s0,a 0, r0, . . . ,st} denotes the trajectory observed up to time t. This belief captures the agent's uncertainty about the underlying transition and reward functions. The transition and reward functions can then be defined in expectation over this posterior, effectively conditioning decision-making on the belief bt. When the environment is driven by hidden contextual variables or latent task parameters, such as in CMDPs or HiP-MDPs-this belief can be interpreted as a distribution over these latent variables. In this view, BAMDPs provide a non-parametric framework for reasoning over hidden structure, while approaches like ours explicitly model such latent variables and infer their posterior distributions using amortized inference. Both aim to enable adaptive planning and learning under uncertainty, but differ in how latent structure is represented and ","citing_arxiv_id":"2605.16054"},{"n":1,"role":"method","polarity":"use_method","paper_title":"GeoQuery: Geometry-Query Diffusion for Sparse-View Reconstruction","primary_cat":"cs.CV","context_text":"− 1 2 (x−𝜇) ⊤Σ−1 (x−𝜇) \u0013 .(1) The covariance is optimized via a factored representation Σ= RSS⊤R⊤ to ensure semi-definiteness. To render the scene, 3D Gaussians are projected into 2D image space. The final color 𝐶 of a pixel is computed by alpha-blending 𝑁 ordered Gaussians overlapping the pixel: 𝐶= 𝑁∑︁ 𝑖=1 𝑐𝑖𝛼𝑖𝐺 2𝐷 𝑖 (x) 𝑖−1Ö 𝑗=1 (1−𝛼 𝑗𝐺 2𝐷 𝑗 (x)),(2) where 𝑐𝑖, 𝛼𝑖, and𝐺 2𝐷 𝑖 (x) denote the color, opacity, and the evaluation of the𝑖-th projected 2D Gaussian at pixel positionx, respectively. 3.2 Diffusion Models Diffusion models [Ho et al. 2020; Rombach et al. 2022; Song et al. 2020] learn a data distribution 𝑝data (x) via iterative denoising. A forward process progressively perturbs data by adding Gaussian","citing_arxiv_id":"2605.12399"},{"n":1,"role":"method","polarity":"use_method","paper_title":"Polyphonia: Zero-Shot Timbre Transfer in Polyphonic Music with Acoustic-Informed Attention Calibration","primary_cat":"cs.SD","context_text":"Interpolation achieves lower entropy, reflecting a sharper distri- bution critical for precise localization. For more details of this analysis, please refer toApp. F. mtext ∈ {0,1} Ly to isolate the target entity within the prompt Ytgt. Let Itgt denote the set of token indices of the target subject (e.g., \"violin\"). The mask is defined as: mtext i = ( 1,ifi∈ I tgt 0,otherwise (12) Subsequently, a Spatio-Textual Bias MatrixB is synthesized via the outer product of g=Flatten(G)∈R Lz and the token mask mtext. This bias is injected into the pre-Softmax attention energy to regulate the attention distribution: Ebias = QK ⊤ √ d +λ·B,B=g⊗m text ∈R Lz×Ly (13) Attnmod(Q, K, V) =Softmax(E bias)V(14) where λ is a scalar controlling modulation strength.","citing_arxiv_id":"2605.10203"}]},"authors":[]}}