# Auto-generated: ECCV2026 paper notes ignore
# 由 src/sync_notes.py 根据 TODO.md 自动生成

# 默认忽略所有笔记
*.md
**/*.md

# 保留元数据文件
!TODO.md
!INDEX.md
!index.md

# 排除已完成笔记所在的子目录
!3d_vision/
!ai_safety/
!aigc_detection/
!audio_speech/
!autonomous_driving/
!causal_inference/
!hallucination/
!human_understanding/
!image_generation/
!image_restoration/
!information_retrieval/
!interpretability/
!llm_agent/
!llm_nlp/
!llm_pretraining/
!llm_safety/
!medical_imaging/
!model_compression/
!multi_agent/
!multimodal_vlm/
!object_detection/
!optimization/
!others/
!reinforcement_learning/
!remote_sensing/
!robotics/
!segmentation/
!self_supervised/
!video_generation/
!video_understanding/
!vlm_efficiency/
!vlm_reasoning/

# 已完成笔记 (423 篇)
!3d_vision/ac3s_adaptive_conditioning_for_3d-aware_synthetic_data_generation.md
!3d_vision/aerialmetric_benchmarking_and_adapting_uav_monocular_metric_depth_estimation_in_.md
!3d_vision/agentic_collaborative_cognition_for_zero-shot_3d_understanding.md
!3d_vision/airzoo_a_unified_large-scale_dataset_for_grounding_aerial_geometric_3d_vision.md
!3d_vision/anymatch_supercharging_universal_multi-modal_image_matching_with_large-scale_sin.md
!3d_vision/audio-visual_camera_pose_estimation_with_passive_scene_sounds_and_in-the-wild_vi.md
!3d_vision/brepllm_enabling_large_language_models_to_understand_boundary_representations.md
!3d_vision/capacity-controlled_multi-view_stylization_of_3d_gaussian_splatting.md
!3d_vision/defensesplat_enhancing_the_robustness_of_3d_gaussian_splatting_via_frequency-awa.md
!3d_vision/deworldsg_depth-aware_3d_semantic_scene_graph_generation_via_world-model_priors.md
!3d_vision/diffusion-based_material_regularization_for_physics-based_inverse_rendering.md
!3d_vision/diffusion_based_material_regularization_for_physics_based_inverse_rendering.md
!3d_vision/dlgstream_dynamic_language-embedded_guassian_splatting_for_open-vocabulary_enabl.md
!3d_vision/epo_boosting_3d_foundation_models_with_edge-based_pose_optimization.md
!3d_vision/face_anything_4d_face_reconstruction_from_any_image_sequence.md
!3d_vision/fica_feed-forward_instant_gaussian_codec_avatars_from_a_single_portrait_image.md
!3d_vision/g2p_gaussian-to-point_attribute_alignment_for_boundary-aware_3d_segmentation.md
!3d_vision/gaussian_belief_propagation_network_for_depth_completion.md
!3d_vision/gaussiangpt_towards_autoregressive_3d_gaussian_scene_generation.md
!3d_vision/gausslite_online_task-conditioned_3d_gaussian_splatting_for_real-time_robotic_mapping.md
!3d_vision/gausslite_task_conditioned_3dgs_mapping.md
!3d_vision/gena3d_generative_amodal_3d_modeling_by_bridging_2d_priors_and_3d_coherence.md
!3d_vision/gensp_consistent_spherical_parameterization_via_learning_shape_generative_models.md
!3d_vision/geo-id_test-time_geometric_consensus_for_cross-view_consistent_intrinsics.md
!3d_vision/geometry-aware_style_transfer_in_3d_gaussian_splatting.md
!3d_vision/graft_geometric_refinement_and_fitting_transformer_for_human_scene_reconstructio.md
!3d_vision/hat-4d_lifting_monocular_video_for_4d_multi-object_interactions_via_human-agent_.md
!3d_vision/hierarchical_3d_scene_graph_construction_and_belief-based_planning_for_semantic_.md
!3d_vision/improving_sparse-view_3dgs_generalization_via_flat_minima_optimization.md
!3d_vision/ink3d_sculpting_3d_assets_with_extremely_complex_textures_via_video_generative_m.md
!3d_vision/interact3d_compositional_3d_generation_of_interactive_objects.md
!3d_vision/janusmesh_fast_and_zero-shot_3d_visual_illusion_generation_via_cross-space_denoi.md
!3d_vision/large-scale_high-quality_3d_gaussian_head_reconstruction_from_multi-view_capture.md
!3d_vision/learning_video_dynamics_with_predictive_differentiable_rendering.md
!3d_vision/luna_learning_universal_3d_human_animation_beyond_skinning.md
!3d_vision/megas_thermomechanical_dynamic_gaussian_splatting_for_thermophysical_scene_editi.md
!3d_vision/monocular_avatar_reconstruction_via_cascaded_diffusion_priors_and_uv-space_diffe.md
!3d_vision/monte_carlo_energy_aggregation_for_mobile_3d_gaussian_splatting.md
!3d_vision/multi4d_high-fidelity_dynamic_gaussian_splatting_via_multi-level_competitive_all.md
!3d_vision/one_video_one_world_turning_monocular_video_into_physical_4d_scenes.md
!3d_vision/op3dsg_open-vocabulary_part-aware_3d_scene_graph_generation_for_real-world_envir.md
!3d_vision/orthotrack_continuous_6-dof_uav_trajectory_estimation_anchored_in_public_orthoph.md
!3d_vision/pano3d_unified_3d_reconstruction_and_panoptic_segmentation.md
!3d_vision/physically_grounded_3d_generative_reconstruction_under_hand_occlusion_using_prop.md
!3d_vision/poseshield_neural_collision_fields_for_human_self-collision_resolution.md
!3d_vision/progressive_pose-guided_4d_animal_reconstruction_from_monocular_video.md
!3d_vision/raga_real_time_ray_traced_gaussian_shadow_casting_for_3dgs_avatar-scene_interact.md
!3d_vision/reper-360_releasing_perspective_priors_for_360circ_depth_estimation_via_self-mod.md
!3d_vision/semcityloc_aerial_6dof_localization_using_semantic_3d_city_models.md
!3d_vision/shellmaker_language-guided_exterior_completion_under_structural_constraints.md
!3d_vision/sk-adapter_skeleton-based_structural_control_for_native_3d_generation.md
!3d_vision/skel-cf_coarse-to-fine_biomechanical_skeleton_and_surface_mesh_recovery.md
!3d_vision/sonar-mast3r_real-time_opti-acoustic_fusion_in_turbid_unstructured_environments.md
!3d_vision/specsia_stylization_dataset_for_novel-view_enhancement_in_drawing-based_3d_anima.md
!3d_vision/spectralsplats_robust_differentiable_tracking_via_spectral_moment_supervision.md
!3d_vision/stereogs_sparse-view_3d_gaussian_splatting_via_stereo_priors.md
!3d_vision/tora_topological_representation_alignment_for_3d_shape_assembly.md
!3d_vision/towards_in-the-wild_egocentric_3d_hand-object_pose_estimation.md
!3d_vision/unipr-3d_towards_universal_visual_place_recognition_with_visual_geometry_grounde.md
!3d_vision/unitrisplat_a_unified_3d_gaussian_splatting_framework_with_uniform_spherical_ras.md
!3d_vision/urope_universal_relative_position_embedding_across_geometric_spaces.md
!3d_vision/viewsplat_view-adaptive_3d_gaussian_splatting_for_feed-forward_synthesis.md
!3d_vision/vitality-aware_compression_for_efficient_image-to-shape_diffusion_transformers.md
!3d_vision/voca_visual_odometry_with_codec_awareness.md
!3d_vision/volsplat_rethinking_feed-forward_3d_gaussian_splatting_with_voxel-aligned_predic.md
!3d_vision/walking_in_the_implicit_interactive_world_exploration_via_neural_scene_represent.md
!3d_vision/zero-shot_depth_from_defocus.md
!ai_safety/a_classifier-agnostic_zero-shot_adversarial_attack_detection_via_clip.md
!ai_safety/exploiting_local_flatness_for_efficient_out_of_distribution_detection.md
!ai_safety/gradiaguard_a_gradient-based_shield_against_vjpeg-adversarial_attacks.md
!ai_safety/improving_adversarial_robustness_via_activation_amplification_and_attenuation.md
!ai_safety/ireu_identity-related_encoder-only_unlearning_for_customized_portrait_generation.md
!ai_safety/moiré_video_authentication_a_physical_signature_against_ai_video_generation.md
!ai_safety/protofair_fair_self-supervised_contrastive_learning_via_pseudo-counterfactual_pa.md
!aigc_detection/diffnet_document_tampering_localization.md
!aigc_detection/multi_task_bayesian_in_context_learning.md
!aigc_detection/trustworthy_image_authentication_using_forensic_knowledge_graphs.md
!audio_speech/a_first_exploration_of_neuromorphic_ot-cfm_for_multi-speaker_vsr.md
!audio_speech/mg-rwkv_multi-grained_context-aware_rwkv_for_temporal_forgery_localization.md
!audio_speech/olive_view-augmented_latent_prediction_with_waveform_reconstruction_for_speech_ssl.md
!audio_speech/see_sniff_learning_visuo-olfactory_representations.md
!audio_speech/sparsity-inducing_divergence_losses_for_biometric_verification.md
!audio_speech/step-by-step_video-to-audio_synthesis_via_negative_audio_guidance.md
!audio_speech/swiftaudio_data_efficient_caption_only_distillation.md
!autonomous_driving/2k_retrofit_entropy-guided_efficient_sparse_refinement_for_high-resolution_3d_ge.md
!autonomous_driving/a_step_wise_self-training_approach_leveraging_natural_language_for_weakly_supervi.md
!autonomous_driving/astad_asymmetric_style_transfer_for_synthetic-to-real_adaptation_in_autonomous_d.md
!autonomous_driving/cooperscene_multi-modal_cooperative_autonomy_benchmark_with_c-v2x_communication_.md
!autonomous_driving/deconfounded_lifelong_learning_for_autonomous_driving_via_dynamic_knowledge_spac.md
!autonomous_driving/driver-wm_a_driver-centric_traffic-conditioned_latent_world_model_for_in-cabin_d.md
!autonomous_driving/driveva_video_action_models_are_zero-shot_drivers.md
!autonomous_driving/driveweaver_point-conditioned_video_inpainting_for_controllable_vehicle_insertio.md
!autonomous_driving/explorevla_dense_world_modeling_and_exploration_for_end-to-end_autonomous_drivin.md
!autonomous_driving/flm-occ_feed-forward_likelihood_maximization_for_efficient_indoor_occupancy_pred.md
!autonomous_driving/frozendrive_zero-shot_text-guided_driving_scene_generation_and_data_augmentation.md
!autonomous_driving/geometry-preserving_in_3d_gaussian_splatting_for_lidar-camera_extrinsic_calibrat.md
!autonomous_driving/hesim_hybrid_event_frame_sensor.md
!autonomous_driving/hilda_hierarchical_distillation_with_diffusion_for_advancing_self-supervised_lid.md
!autonomous_driving/horizon3d_sparse_radar-camera_fusion_for_long-range_3d_perception_in_autonomous_.md
!autonomous_driving/hsdf-lane_height-aligned_signed_distance_field_with_semantic_lane_prior_for_3d_l.md
!autonomous_driving/lagen_towards_autoregressive_lidar_scene_generation.md
!autonomous_driving/lead-m3d_leveraging_asymmetric_distillation_for_real-time_monocular_3d_detection.md
!autonomous_driving/long-term_traffic_simulation_via_structured_autoregressive_modeling.md
!autonomous_driving/omninwm_omniscient_driving_navigation_world_models.md
!autonomous_driving/open-vocabulary_bev_segmentation_with_3d-aware_geometric_constraints.md
!autonomous_driving/plot_pseudo-labeling_via_object_tracking_for_monocular_3d_object_detection.md
!autonomous_driving/prioreye_geospatial_visual_priors_for_end-to-end_autonomous_driving.md
!autonomous_driving/real-time_source-free_object_detection.md
!autonomous_driving/resolve_a_multi-resolution_and_multi-modal_dataset_for_roadside_cooperative_perc.md
!autonomous_driving/rethinking_training_inference_for_forecasting_linking_winner-take-all_back_to_gm.md
!autonomous_driving/streaming_dense_voxel_representations_for_3d_occupancy_prediction.md
!autonomous_driving/towards_metric-agnostic_trajectory_forecasting.md
!autonomous_driving/understanding_cross-rig_generalization_in_automotive_perception_a_multi-rig_benc.md
!autonomous_driving/unidrive-wm_unified_understanding_planning_and_generation_world_model_for_autono.md
!autonomous_driving/united_unified_temporal_diffusion_for_joint_perception_and_planning_in_autonomou.md
!autonomous_driving/unveiling_transferability_in_trajectory_prediction_via_latent_scene_embeddings.md
!autonomous_driving/warpi2i_image_warping_for_image-to-image_translation.md
!causal_inference/fd2_a_dedicated_framework_for_fine-grained_dataset_distillation.md
!hallucination/from_hallucination_to_grounding_diagnosing_visual_spatial_intelligence_via_crisp.md
!hallucination/no_place_to_hide_benchmarking_video_hallucination_with_background-controlled_pai.md
!human_understanding/backtranslation20_--_a_linguistically_motivated_metric_to_assess_sign_language_p.md
!human_understanding/dress-ed_instruction-guided_editing_for_virtual_try-on_and_try-off.md
!human_understanding/facemoe_mixture_of_experts_for_low-resolution_face_recognition.md
!human_understanding/flowerdance_meanflow_for_efficient_and_refined_3d_dance_generation.md
!human_understanding/interedit_navigating_text-guided_3d_dyadic_human_motion_editing.md
!human_understanding/multi-scale_object-aware_gaze_estimation_via_geometric_reasoning.md
!human_understanding/odoriko_a_shape-aware_multimodal_diffusion_framework_for_human_motion.md
!human_understanding/piavatar_physically_interactive_avatars_via_deformation_gradient_decoupling.md
!human_understanding/reweighting_framewise_attention_in_video_transformers_for_facial_expression_unde.md
!human_understanding/self-supervised_garment_dynamics_with_persistent_wrinkles.md
!human_understanding/sicage_speaker-independent_culture-aware_gesture_generation_using_ted4c-l_datase.md
!human_understanding/signer_temporally_grounded_sign_language_generation_via_time-resolved_conditioni.md
!human_understanding/signet_motion-level_knowledge_transfer_for_cross-language_sign_language_translat.md
!human_understanding/signnet-1m_large-scale_multilingual_sign_language_video_dataset_with_downstream_.md
!human_understanding/synccache_exploiting_asymmetric_dynamics_for_fast_audio-driven_portrait_animatio.md
!human_understanding/text_dictates_music_decorates_energy_based_attention_for_editable_dance_motion_generation.md
!human_understanding/unimotion_a_unified_framework_for_motion-text-vision_understanding_and_generatio.md
!human_understanding/unsupervised_multi-person_tracking_via_point_visual_prompting.md
!image_generation/accelerated_likelihood_maximization_for_diffusion-based_versatile_content_genera.md
!image_generation/advancing_wordart-oriented_scene_text_recognition_datasets_and_methods.md
!image_generation/anchoring_on_reality_breaking_the_pseudo-target_ceiling_in_makeup_transfer.md
!image_generation/avsr-diff_scale-agnostic_diffusion_priors_for_temporally_consistent_arbitrary-sc.md
!image_generation/c3-bench_a_context-aware_change_captioning_benchmark.md
!image_generation/continuous_speculative_decoding_for_autoregressive_image_generation.md
!image_generation/curvature-adaptive_consistency_flow_matching_autonomous_trajectory_optimization_.md
!image_generation/diffusion_integrated_gradients_controllable_path_generation_for_flexible_feature.md
!image_generation/divide_and_conquer_decoupled_representation_alignment_for_multimodal_world_model.md
!image_generation/divrl_disentangled_self-similarity_rewards_for_diverse_subject-driven_generation.md
!image_generation/dont_settle_at_the_mode_mitigating_diversity_collapse_in_pretrained_flow_models_.md
!image_generation/driftscope_measuring_the_hidden_effects_of_diffusion_model_adaptation.md
!image_generation/dti_dynamic_trajectory_initialization_for_generative_face_video_super-resolution.md
!image_generation/dual-end_consistency_model.md
!image_generation/edit_in_2d_verify_in_3d_reinforcement_learning_for_multi-view_consistent_scene_e.md
!image_generation/entropy-controlled_flow_matching.md
!image_generation/fedot_ownership_verification_and_leakage_tracing_via_watermarks_for_federated_ld.md
!image_generation/few-shot_synthetic_image_attribution_identifying_unseen_generators_with_limited_.md
!image_generation/filterless_snapshot_hyperspectral_imaging_using_guided_patch_diffusion.md
!image_generation/focusing_on_what_matters_saliency-harnessing_accurate_routing_for_diffusion_moe.md
!image_generation/fumo_prior-modulated_diffusion_for_single_image_reflection_removal.md
!image_generation/gen2balance_generative_balancing_for_long-tailed_video_action_recognition.md
!image_generation/geoedit_geometry-aware_object_editing_via_dual-branch_denoising.md
!image_generation/h-adapter_pose-robust_hairstyle_transfer_via_attention-derived_source-aligned_ha.md
!image_generation/histogram-constrained_image_generation.md
!image_generation/in-context_region-based_drag_drag_any_region_to_any_shape.md
!image_generation/intermediate_text_representation_guided_text-to-image_generation_for_enhancing_o.md
!image_generation/isac_training_free_instance_to_semantic_attention.md
!image_generation/layout-conditioned_autoregressive_text-to-image_generation_via_structured_maskin.md
!image_generation/learn_once_edit_anywhere_visual_direction_transfer_for_diffusion_models.md
!image_generation/mepa_multi-scale_representation_alignment_for_visual_autoregressive_modeling_wit.md
!image_generation/mgi_member_vs_generated_inference.md
!image_generation/mimflow_integrating_masked_image_modeling_with_normalizing_flows_for_end-to-end_.md
!image_generation/mindflow_harmonizing_cognitive_semantics_and_acoustic_dynamics_for_facial_animat.md
!image_generation/mirrorppr_exemplar-based_portrait_photo_retouching.md
!image_generation/noisetilt_noise-tilted_reverse_kernels_for_diffusion_reward_alignment.md
!image_generation/not_all_prediction_targets_keep_training-free_diffusion_guidance_on_the_manifold.md
!image_generation/obliviate_erasing_concepts_from_autoregressive_image_generation_models.md
!image_generation/otcache_optimal_transport_for_geometry-aware_caching_in_diffusion_models.md
!image_generation/phase-aligned_rope_for_mixed-resolution_diffusion_transformer.md
!image_generation/phyeditbench_a_real-world_multi-stage_benchmark_for_physics-aware_image_editing.md
!image_generation/prompt2effect_training-free_image-to-video_model_specialization_via_lora_generat.md
!image_generation/rethinking_garment_conditioning_in_diffusion-based_virtual_try-on_decouple_dont_.md
!image_generation/revisiting_autoregressive_models_for_generative_image_classification.md
!image_generation/semantic_browsing_controllable_diversity_for_image_generation.md
!image_generation/sonic_spectral_optimization_of_noise_for_inpainting_with_consistency.md
!image_generation/spanning_the_visual_analogy_space_with_a_weight_basis_of_loras.md
!image_generation/srum_fine-grained_self-rewarding_for_unified_multimodal_models.md
!image_generation/symbiotic-moe_unlocking_the_synergy_between_generation_and_understanding.md
!image_generation/text-conditioned_background_generation_for_editable_multi-layer_documents.md
!image_generation/the_illusion_of_high_utility_in_safety_alignment_of_text-to-image_diffusion_mode.md
!image_generation/unitranslator_a_unified_multi-modal_framework_for_end-to-end_in-image_machine_tr.md
!image_generation/unity_attention_flow_networks_for_adaptive_conditioning_in_diffusion.md
!image_generation/universal_image_immunization_against_diffusion-based_image_editing_via_semantic_.md
!image_generation/vidit_visual_direction_transfer.md
!image_generation/vtedit-bench_a_comprehensive_benchmark_for_multi-reference_image_editing_models_.md
!image_restoration/cogsenet_blind_image_deblurring_with_blur-conditioned_semantic_routing_and_expli.md
!image_restoration/fabric_image_demoiréing_benchmark_from_synthesis_to_restoration.md
!image_restoration/fidelity-_and_perception-aware_local_implicit_attention_for_arbitrary-scale_imag.md
!image_restoration/flowdec_temporal_conditional_flow_decorruptor_for_robust_continuous_vision-langu.md
!image_restoration/fma-netpp_motion-_and_exposure-aware_joint_video_super-resolution_and_deblurring.md
!image_restoration/freemef_flexible_frame_mef.md
!image_restoration/freqortho-sr_frequency-guided_orthogonal_expert_learning_for_real-world_image_su.md
!image_restoration/logicir_logic_gate_networks_for_image_restoration.md
!image_restoration/personalization_as_inverse_planning_learning_latent_design_intents_for_agentic_s.md
!image_restoration/spectral_and_trajectory_regularization_for_diffusion_transformer_super-resolutio.md
!image_restoration/tasktok_delving_into_task_tokens_for_task-driven_image_restoration.md
!image_restoration/uhd-mff_shattering_barriers_in_uhd_multi-focus_image_fusion.md
!information_retrieval/hyfl-clip_hyperbolic_fine-tuning_of_clip_for_robust_long-context_understanding.md
!information_retrieval/lightstar_efficient_visual_document_retrieval_via_lightweight_selection_with_vis.md
!interpretability/evaluating_the_interpretability_of_sparse_autoencoders_with_concept_annotations.md
!interpretability/on_the_faithfulness_of_post-hoc_concept_bottleneck_models.md
!llm_agent/guide_resolving_domain_bias_in_gui_agents_through_real-time_web_video_retrieval_.md
!llm_agent/nala_a_3d_native_llm_layout_agent_for_high-quality_3d_scene_generation.md
!llm_agent/think_while_you_map_asynchronous_vision-language_agents_for_incremental_3d_scene.md
!llm_agent/viscritic_visual_state_comparison_as_process_reward_for_gui_agents.md
!llm_nlp/sam2matting_generalized_image_and_video_matting.md
!llm_pretraining/360anything_geometry-free_lifting_of_images_and_videos_to_360.md
!llm_pretraining/gryphone_symbol-aware_masked_diffusion_for_structural_refinement_in_offline_hand.md
!llm_safety/learning_to_compose_revisiting_proxy_task_design_for_zero-shot_composed_image_re.md
!llm_safety/neural_gate_mitigating_privacy_risks_in_lvlms_via_neuron-level_gradient_gating.md
!llm_safety/reshift_aha-moment-driven_reasoning-level_backdoor_attacks_on_vision-language_mo.md
!llm_safety/slowba_an_efficiency_backdoor_attack_towards_vlm-based_gui_agents.md
!llm_safety/towards_benign_memory_forgetting_for_selective_multimodal_large_language_model_u.md
!medical_imaging/3d_field_of_junctions_a_noise-robust_training-free_structural_prior_for_volumetr.md
!medical_imaging/a_mechanism-driven_theory_of_phase_transitions_in_active_learning.md
!medical_imaging/active_view_selection_with_perturbed_gaussian_ensemble_for_tomographic_reconstru.md
!medical_imaging/biomedvr_confusion-aware_mixture-of-prompt_experts_for_biomedical_visual_reprogr.md
!medical_imaging/brainfibre_a_foundation_model_via_information_decomposition_for_brain_microstruc.md
!medical_imaging/brainriem_riemannian_prototype_learning_for_source-free_cross-site_brain_network.md
!medical_imaging/dual-prior_guided_null-space_learning_with_mixture-of-splines_for_arbitrary_medi.md
!medical_imaging/from_reconstruction_to_decision_a_post-encoder_plug-in_adapter_for_curvilinear_s.md
!medical_imaging/histopathology_multi-modal_embedding_for_pathology_composed_retrieval.md
!medical_imaging/medcagd_context-aware_gated_decoder_for_efficient_medical_image_segmentation.md
!medical_imaging/ngps_structure-preserving_self-supervised_denoising_via_neighbor-guided_patch_sa.md
!medical_imaging/render-fm_feedforward_model_for_real-time_photorealistic_volumetric_rendering.md
!medical_imaging/skin_r1_clinical_knowledge_guided_dermatological_diagnosis_using_vision_language_models.md
!medical_imaging/skin_r1_dermatological_diagnosis.md
!medical_imaging/taxomil_taxonomy-constrained_learning_for_hierarchical_whole_slide_image_analysi.md
!model_compression/condensing_large-scale_datasets_directly_with_minimal_information_loss.md
!model_compression/distill_on_a_diet_efficient_knowledge_distillation_via_learnable_data_pruning.md
!model_compression/distill_once_adapt_life-long_exploring_dataset_distillation_for_continual_test-t.md
!model_compression/mambaraw_selective_state_space_modeling_for_efficient_4k_raw_image_reconstructio.md
!model_compression/mixtta_low-rank_cross-channel_mixing_for_reliable_test-time_adaptation.md
!model_compression/mlvc_multi-platform_learned_video_codec_for_real-world_deployment.md
!model_compression/on_the_vulnerability_of_parameter-level_defenses_to_model_merging.md
!model_compression/raysup_ultra-light_universal_feature_upsampling_via_geometry-aware_ray_represent.md
!model_compression/structural_assessment_for_understanding_and_guiding_dataset_distillation_in_disc.md
!model_compression/structured_hyperedge_adaptation_for_parameter-efficient_fine-tuning_of_vision_tr.md
!model_compression/textds_parameter-efficient_representation_alignment_for_scene_text_detection_und.md
!multi_agent/quantv2x_a_fully_quantized_multi-agent_system_for_cooperative_perception.md
!multimodal_vlm/adaboosting_text_prompts_for_vision-language_models.md
!multimodal_vlm/adapt_attention_dynamics_alignment_with_preference_tuning_for_faithful_mllms.md
!multimodal_vlm/anchored_not_graded_vision-language_models_fail_at_slant-from-texture_perception.md
!multimodal_vlm/curvature-guided_mixing_for_mllm_adaptation.md
!multimodal_vlm/dicobench_benchmarking_multi-image_fine-grained_perception_via_differential_and_.md
!multimodal_vlm/domain_arithmetic_one-shot_vla_adaptation_under_environmental_shifts.md
!multimodal_vlm/edges_before_embeddings_a_confidence-aware_blur_gate_for_vision-language_pipelin.md
!multimodal_vlm/egosat_a_comprehensive_benchmark_of_egocentric_streaming_interaction_understandi.md
!multimodal_vlm/eraselora_mllm-driven_foreground_exclusion_and_background_subtype_aggregation_fo.md
!multimodal_vlm/evaluating_and_enhancing_negation_comprehension_in_remote_sensing_mllms.md
!multimodal_vlm/explicit_logic_channel_for_validation_and_enhancement_of_mllms_on_zero-shot_task.md
!multimodal_vlm/generating_a_paracosm_for_training-free_zero-shot_composed_image_retrieval.md
!multimodal_vlm/gkdt_general_keypoint_detection_transformer.md
!multimodal_vlm/identifying_and_resolving_pitfalls_of_knowledge-based_vqa_benchmarks_auditing_re.md
!multimodal_vlm/invoice_haystack_benchmarking.md
!multimodal_vlm/layer-specific_prompt_fusion_discovery_via_differentiable_search_in_vision_found.md
!multimodal_vlm/learning_from_failure_inference-time_self-improvement_for_computer-use_agents.md
!multimodal_vlm/learning_to_deny_action_denial_in_multimodal_large_language_models.md
!multimodal_vlm/magic-mm-embedding_towards_visual-token-efficient_universal_multimodal_embedding.md
!multimodal_vlm/mirror_aligning_semantic_relations_from_language_to_image_via_gromov--wasserstei.md
!multimodal_vlm/motionatlas_detailed_region_captioning_for_motion-centric_videos.md
!multimodal_vlm/mova_asymmetric_dual_projections_modular_video_text_alignment.md
!multimodal_vlm/mova_learning_asymmetric_dual_projections_for_modular_long_video-text_alignment.md
!multimodal_vlm/multi-modality_image_fusion_under_adverse_weather_mask-guided_feature_restoratio.md
!multimodal_vlm/negas_negative_label_guided_attention_and_scoring_for_out-of-distribution_object.md
!multimodal_vlm/panogrounder_bridging_2d_and_3d_with_panoramic_scene_representations_for_vlm-bas.md
!multimodal_vlm/proactivebench_benchmarking_proactiveness_in_multimodal_large_language_models.md
!multimodal_vlm/rank-aware_hyperbolic_alignment_for_vision-language_dataset_distillation.md
!multimodal_vlm/region-aware_multimodal_large_language_model_via_slowfast_tokenization_and_pseud.md
!multimodal_vlm/rsiccllm_a_multimodal_large_language_model_for_remote_sensing_image_change_capti.md
!multimodal_vlm/skin-r1_clinical_knowledge-guided_dermatological_diagnosis_using_vision-language.md
!multimodal_vlm/solving_semi-supervised_few-shot_learning_from_an_auto-annotation_perspective.md
!multimodal_vlm/stardojo_benchmarking_open-ended_behaviors_of_agentic_multimodal_llms_in_product.md
!multimodal_vlm/staying_vigilant_mitigating_visual_laziness_via_counterfactual_visual_alignment_.md
!multimodal_vlm/stochast_learning_with_stochastic_turn_depth_for_visual_instruction_tuning.md
!multimodal_vlm/unitac_a_unified_multimodal_model_for_cross-sensor_tactile_understanding_and_gen.md
!multimodal_vlm/visnec_measuring_and_leveraging_visual_necessity_for_multimodal_instruction_tuni.md
!multimodal_vlm/visreflect_latent_visual_reflection_for_fine-grained_perception_in_long_visual_c.md
!multimodal_vlm/wake_up_for_touch_mask-isolated_tactile_alignment_learning_in_mllms.md
!multimodal_vlm/when_sinks_help_or_hurt_unified_framework_for_attention_sink_in_large_vision-lan.md
!object_detection/adaptive_spectrum-aware_feature_disentangled_network_for_small_object_detection.md
!object_detection/cmds-ad_cross-modal_dual-stream_decoupling_for_few-shot_anomaly_detection.md
!object_detection/denoising-enhanced_coarse-to-fine_infrared_small_target_detection_with_attention.md
!object_detection/efficient_rgb-t_object_detection_via_sparse_cross-modality_fusion.md
!object_detection/following_the_flow_advection-consistent_modeling_for_event-based_small_object_de.md
!object_detection/logico_a_unified_framework_for_logical_and_structural_anomaly_detection.md
!object_detection/m4-sar_a_multi-resolution_multi-polarization_multi-scene_multi-source_dataset_an.md
!object_detection/match_flow_matching_for_multi-view_anomaly_detection.md
!object_detection/mspl_multi-step_pseudo-labeling_for_open-vocabulary_object_detection.md
!object_detection/ps-mot_cultivating_instance_awareness_from_point_seeds_for_multi-object_tracking.md
!object_detection/rethinking_continual_anomaly_detection_on_the_edge_benchmarking_under_realistic_.md
!object_detection/rethinking_prototype-based_similarity_learning_for_few-shot_object_detection.md
!object_detection/robust_zero-shot_anomaly_detection_under_limited_auxiliary_anomaly_priors.md
!object_detection/s2-fracmix_label-preserving_self-saliency_mixup_augmentation.md
!object_detection/svcbench_a_streaming_video_counting_benchmark_for_spatial-temporal_state_mainten.md
!object_detection/the_label_imitation_game_turing_test_network_for_zero-shot_pseudo-label_pruning.md
!object_detection/towards_continual_open-vocabulary_object_detection.md
!object_detection/vlod-tta_test-time_adaptation_of_vision-language_object_detectors.md
!optimization/rbe-flow_recurrent_bayesian_estimation_on_feature_manifolds_for_cross-modal_regi.md
!optimization/son_goku_graph_coloring_mtl.md
!others/articulat3d_reconstructing_articulated_digital_twins_from_monocular_videos_with_.md
!others/fedlas_feature-modulated_bidirectional_label_smoothing_for_neural_network_calibr.md
!others/geometric_gradient_rectification_for_safe_open-set_semi-supervised_learning.md
!others/geometry-anchored_transport_framework_for_exemplar-free_class-incremental_learni.md
!others/graph_coloring_for_multi-task_learning.md
!others/hybrid_event_frame_sensors_modeling_calibration_simulation.md
!others/intrinsically_stable_spiking_neural_networks_overcoming_the_performance_barrier_.md
!others/lie_group_diffusion_models_for_hardware_aware_quantum_circuit_synthesis.md
!others/lost_in_the_tail_addressing_geographic_imbalance_in_urban_visual_place_recogniti.md
!others/match-any-events_zero-shot_motion-robust_feature_matching_across_wide_baselines_.md
!others/nurbs_splatting_a_unified_differentiable_rendering_framework_for_vector_graphics.md
!others/optically_dense_nanowire_metamaterials_transparent_polarization.md
!others/pointer-cad_v2_plan-then-construct_cad_generation_with_dimension-aware_parametri.md
!others/recovery_operators_in_quasi_nelson_logic_the_prelinear_case.md
!others/seeing_touch_from_motion_a_unified_modality-aware_visuo-tactile_policy_with_tact.md
!others/spectral_gating_via_damped_oscillations_for_adaptive_implicit_neural_representat.md
!others/steerable_isotropic_vector-valued_anisotropic_radial_basis_functions.md
!others/vector_scaffolding_inter-scale_orchestration_for_differentiable_image_vectorizat.md
!reinforcement_learning/elva_exploring_ranking-driven_universal_multimodal_retrieval.md
!remote_sensing/tessellating_the_earth.md
!robotics/a_scalar_per_patch_from_pre-trained_vits_enables_fast_moving_navigation_in_the_r.md
!robotics/affogato_open-vocabulary_affordance_grounding_with_automated_data_generation_at_.md
!robotics/autospeed_annotation-free_stage-adaptive_motion_speed_learning_for_robot_manipul.md
!robotics/e-vla_event-augmented_vision-language-action_model_for_dark_and_blurred_scenes.md
!robotics/empathic_robots_exploring_the_role_of-empathy_in_vision-language_action_models.md
!robotics/libero-safety_a_comprehensive_benchmark_for_physical_and_semantic_safety_in_visi.md
!robotics/navwm_a_unified_navigation_world_model_for_foresight-driven_planning.md
!robotics/policytrim_boosting_intrinsic_policy_efficiency_of_vision-language-action_models.md
!robotics/pondering_the_way_spatial-perceiving_world_action_model_for_embodied_navigation.md
!robotics/pose_anything_anywheremodel-free_object_poses_from_arbitrary_references.md
!robotics/revisiting_parameter_redundancy_in_vision-language-action_models_insights_from_v.md
!robotics/roboatlas_contextual_active_slam.md
!robotics/towards_generalizable_robotic_manipulation_in_dynamic_environments.md
!robotics/vla_knows_its_limits_adaptive_execution_horizons_for_robot_policies.md
!robotics/zr0_dense_embodied_chain_of_thought_vla.md
!segmentation/affmae_scalable_vision_pre-training_for_high-resolution_microscopy_segmentation_.md
!segmentation/delayed_bidirectional_alignment_via_disentangled_audio_semantics_for_audio-visua.md
!segmentation/et-sam_efficient_point_prompt_prediction_in_sam_for_unified_scene_text_detection.md
!segmentation/fevos_foresight_expression_video_object_segmentation.md
!segmentation/forget_anticipate_and_adapt_test_time_training_for_long_videos.md
!segmentation/hierarchical_spatial_and_channel_aggregation_for_cross-domain_few-shot_segmentat.md
!segmentation/mobilemanibench_simplifying_model_verification_for_mobile_manipulation.md
!segmentation/moduseg_decoupling_object_discovery_and_semantic_retrieval_for_training-free_wea.md
!segmentation/residual-guided_expert_specialization_for_incomplete_multimodal_learning.md
!segmentation/sarif_segment_anything_for_robust_image_forensics.md
!segmentation/segmenting_fast_and_slow_real-time_open-vocabulary_video_instance_segmentation_w.md
!segmentation/skelem_training-signal_decoupling_of_skeleton_and_diffusion_for_self-supervised_.md
!segmentation/steerable_visual_representations.md
!segmentation/toward_robust_in-context_segmentation_via_concept_guidance.md
!self_supervised/explore_expert_patch-level_loss_routing_for_multi-objective_masked_image_modelin.md
!self_supervised/from_phase_to_phenomenon_self-supervised_learning_of_subsurface_scattering_with_.md
!self_supervised/zipfian_adaptive_loss_for_neural_compression.md
!video_generation/ahoy_animatable_humans_under_occlusion_from_youtube_videos_with_gaussian_splatti.md
!video_generation/ar-copo_align_autoregressive_video_generation_with_contrastive_policy_optimizati.md
!video_generation/avtok_1d_unified_tokenization_for_holistic_audio-video_generation.md
!video_generation/controllable_egocentric_video_generation_via_occlusion-aware_sparse_3d_hand_join.md
!video_generation/customx_unified_character_action_and_scene_customization_in_video_world_models.md
!video_generation/emosh_expressive_motion_and_shape_disentanglement_for_human_animation.md
!video_generation/event-driven_video_generation.md
!video_generation/geonvs_geometry_grounded_video_diffusion_for_novel_view_synthesis.md
!video_generation/latsearch_latent_reward-guided_search_for_faster_inference-time_scaling_in_video.md
!video_generation/learning_transferable_dynamics_priors_from_action_to_world_modeling.md
!video_generation/liveedit_towards_real-time_diffusion-based_streaming_video_editing.md
!video_generation/lumos-nexus_efficient_frequency_bridging_with_homogeneous_latent_space_for_video.md
!video_generation/memlearner_learning_to_query_context_memory_for_video_world_models.md
!video_generation/mmcontrol_unified_multi-modal_control_for_joint_audio-video_generation.md
!video_generation/next-frame_decoding_for_ultra-low-bitrate_image_compression_with_video_diffusion.md
!video_generation/phygdpo_physics-aware_groupwise_direct_preference_optimization_for_physically_co.md
!video_generation/physics_question_scene_graph_fine-grained_evaluation_of_physical_plausibility_in.md
!video_generation/physrag_enhancing_physics-awareness_in_video_generation_via_retrieval-augmented_.md
!video_generation/refalign_representation_alignment_for_reference-to-video_generation.md
!video_generation/salt_self-consistent_distribution_matching_with_cache-aware_training_for_fast_vi.md
!video_generation/sift_self-imagination_fine-tuning_for_physically_plausible_motion_in_video_diffu.md
!video_generation/streamedit_training-free_video_editing_via_few-step_streaming_video_generation.md
!video_generation/taming_text-to-sounding_video_generation_via_advanced_modality_condition_and_int.md
!video_generation/your_data_manifold_is_secretly_a_reward_model_shell-lcc_for_text-to-video_genera.md
!video_understanding/bridging_videoqa_and_video-guided_agentic_tasks_via_generalized_keyframe_extract.md
!video_understanding/egoexo-con_exploring_view-invariant_video_temporal_understanding.md
!video_understanding/hiedg_a_hierarchical_discrete_geometry-guided_framework_for_multi-animal_trackin.md
!video_understanding/mass_motion-aligned_selective_scan_for_refinement_in_flow-based_video_frame_inte.md
!video_understanding/mavfusion_efficient_infrared_and_visible_video_fusion_via_motion-aware_sparse_in.md
!video_understanding/onpoint_offline-to-online_multi-level_distillation_for_point-supervised_online_t.md
!video_understanding/pa-vad_diffusion-based_pseudo-only_video_anomaly_detection_via_domain-aligned_me.md
!video_understanding/sfdatrack_generalized_source-free_domain_adaptive_tracking_under_adverse_weather.md
!video_understanding/sink-token-aware_pruning_for_fine-grained_video_understanding_in_efficient_video.md
!video_understanding/towards_long-form_spatio-temporal_video_grounding.md
!video_understanding/triangular_consistency_as_a_universal_constraint_for_learning_optical_flow.md
!video_understanding/visual_dubbing_pipeline_with_diffusion_models_for_video_dubbing.md
!vlm_efficiency/accelerating_multimodal_large_language_models_with_prior-corrected_token_reducti.md
!vlm_efficiency/hsd_training-free_acceleration_for_document_parsing_vision-language_models_with_.md
!vlm_efficiency/paying_more_attention_to_visual_tokens_in_self-evolving_large_multimodal_models.md
!vlm_efficiency/resilphase_plug-and-play_phase_mapping_and_noise-resilient_macro-trajectory_extr.md
!vlm_efficiency/smart_when_is_it_actually_worth_expanding_a_speculative_tree.md
!vlm_efficiency/spectral_evolution-guided_token_pruning_in_multimodal_large_language_models.md
!vlm_efficiency/viq_text-aligned_visual_quantized_representations_at_any_resolution.md
!vlm_efficiency/zero-shot_quantization_for_object_detectors_using_off-the-shelf_generative_model.md
!vlm_reasoning/are_video_reasoning_models_ready_to_go_outside.md
!vlm_reasoning/dense_reward_for_multi-view_3d_reasoning_with_global_maps_and_local_views.md
!vlm_reasoning/e-tts_a_new_embodied_test-time_scaling_framework_for_robotic_manipulation.md
!vlm_reasoning/egovita_learning_to_plan_and_verify_for_egocentric_video_reasoning.md
!vlm_reasoning/gaia_a_data_flywheel_system_for_training_gui_test-time_scaling_critic_models.md
!vlm_reasoning/generative_lane_topology_reasoning_via_autoregressive_model_with_geometry_prior.md
!vlm_reasoning/hylar_hybrid_latent_reasoning_with_decoupled_policy_optimization.md
!vlm_reasoning/information-regularized_attention_for_visual-centric_reasoning.md
!vlm_reasoning/latent_visual_diffusion_reasoning_with_monte_carlo_tree_search.md
!vlm_reasoning/monosr_open-vocabulary_spatial_reasoning_from_monocular_images.md
!vlm_reasoning/on_test-time_scaling_for_vision-language_models.md
!vlm_reasoning/roadbench_benchmarking_mllms_on_fine-grained_spatial_understanding_and_reasoning.md
!vlm_reasoning/scale_attention_head_scaling_as_a_minimal_adapter_for_spatial_reasoning_in_visio.md
!vlm_reasoning/sciir_a_large-scale_training_dataset_and_benchmark_for_scientific_image_reasonin.md
!vlm_reasoning/sentry_sam2-enhanced_neighbor-aware_and_temporally_reasoned_memory_for_visual_tr.md
!vlm_reasoning/towards_spatial_trace_with_reasoning_in_vision-language_models_for_robotics.md
!vlm_reasoning/videosearch-r1_iterative_video_retrieval_and_reasoning_via_soft_query_refinement.md
!vlm_reasoning/what_if_emulative_simulation_with_world_models_for_situated_reasoning.md
