Ankit Sanjyal

Ankit Sanjyal

Multimodal emotion recognition on CMU-MOSEI faces an extreme imbalance as Happy accounts for 65.9% of samples while three Ekman categories collectively represent under 7%, causing standard fusion models to maximize accuracy by ignoring minority emotions entirely. We present Affect-Diff, a Causal-Diffusion Bridge that addresses this through three jointly trained mechanisms: a NOTEARS-learned causal graph that re-weights modality contributions before fusion, a beta-VAE bottleneck for regularized latent compression, and a stop-gradiented 1D DDPM prior that structures the latent space against majority-class collapse. On 3,292 aligned CMU-MOSEI samples, Affect-Diff achieves validation balanced accuracy 0.384, an 18% relative improvement over the strongest baseline (TETFN: 0.324), while all evaluated baselines produce zero F1 on Fear, Disgust, and Surprise. Ablation studies confirm independent, non-redundant contributions from the diffusion prior (-24% without it) and causal graph (-13%). Notably, only the deterministic-encoder variant detects all six emotion classes, revealing KL regularization strength as a direct lever for minority-class sensitivity.

Ankit Sanjyal

Diffusion models have become a powerful backbone for text-to-image generation, producing high-quality visuals from natural language prompts. However, when prompts involve multiple objects alongside global or local style instructions, the outputs often drift in style and lose spatial coherence, limiting their reliability for controlled, style-consistent scene generation. We present Local Prompt Adaptation (LPA), a lightweight, training-free method that splits the prompt into content and style tokens, then injects them selectively into the U-Net's attention layers at chosen timesteps. By conditioning object tokens early and style tokens later in the denoising process, LPA improves both layout control and stylistic uniformity without additional training cost. We conduct extensive ablations across parser settings and injection windows, finding that the best configuration -- lpa late only with a 300-650 step window -- delivers the strongest balance of prompt alignment and style consistency. On the T2I benchmark, LPA improves CLIP-prompt alignment over vanilla SDXL by +0.41% and over SD1.5 by +0.34%, with no diversity loss. On our custom 50-prompt style-rich benchmark, LPA achieves +0.09% CLIP-prompt and +0.08% CLIP-style gains over baseline. Our method is model-agnostic, easy to integrate, and requires only a single configuration change, making it a practical choice for controllable, style-consistent multi-object generation.

Ankit Sanjyal

High-resolution image synthesis with diffusion models often suffers from energy instabilities and guidance artifacts that degrade visual quality. We analyze the latent energy landscape during sampling and propose adaptive classifier-free guidance (CFG) schedules that maintain stable energy trajectories. Our approach introduces energy-aware scheduling strategies that modulate guidance strength over time, achieving superior stability scores (0.9998) and consistency metrics (0.9873) compared to fixed-guidance approaches. We demonstrate that DPM++ 2M with linear-decreasing CFG scheduling yields optimal performance, providing sharper, more faithful images while reducing artifacts. Our energy profiling framework serves as a powerful diagnostic tool for understanding and improving diffusion model behavior.

Ankit Sanjyal

Neural Radiance Fields (NeRF) have revolutionized 3D scene reconstruction from sparse image collections. Recent work has explored integrating pre-trained vision features, particularly from DINO, to enhance few-shot reconstruction capabilities. However, the effectiveness of such approaches remains unclear, especially in extreme few-shot scenarios. In this paper, we present a systematic evaluation of DINO-enhanced NeRF models, comparing baseline NeRF, frozen DINO features, LoRA fine-tuned features, and multi-scale feature fusion. Surprisingly, our experiments reveal that all DINO variants perform worse than the baseline NeRF, achieving PSNR values around 12.9 to 13.0 compared to the baseline's 14.71. This counterintuitive result suggests that pre-trained vision features may not be beneficial for few-shot 3D reconstruction and may even introduce harmful biases. We analyze potential causes including feature-task mismatch, overfitting to limited data, and integration challenges. Our findings challenge common assumptions in the field and suggest that simpler architectures focusing on geometric consistency may be more effective for few-shot scenarios.