4 citations · 4 across the 12 of their papers we have counts for
9 papers · 1 filter
How Modular Is a Frontier Mixture-of-Experts? A Pre-registered Causal Test in Which Apparent Expert Modularity Mostly Dissolves
Tony Salomone, Deep Gandhi, Ali Asaria
Sparse Mixture-of-Experts (MoE) models route each token to a few of many experts, inviting the hypothesis that experts form functional modules tied to capabilities or languages. We…
Judging to Improve: A De-biased VLM-as-3D-Judge Protocol for Single-Image 3D Generation
Ali Asaria, Tony Salomone, Deep Gandhi
A companion study established a de-biased, cross-model VLM-as-3D-judge that reliably ranks single-image-to-3D mesh quality where cheap geometry and CLIP proxies fall short. This pa…
Train, Retrieve, or Both? A Four-Arm Head-to-Head for Correct Statutory Citation on the Ontario Residential Tenancies Act
Ali Asaria, Tony Salomone, Deep Gandhi
Self-represented tenants, landlords, and help-desk staff need to be pointed at the provision of law that actually governs a question, with a correct statutory citation. We study th…
A Cross-Model VLM-Judge Protocol for Single-Image 3D Mesh Quality (and Why Cheap Proxies Fall Short)
Ali Asaria, Tony Salomone, Deep Gandhi
Single-image-to-3D generators are improving quickly, but there is no agreed, human-free way to tell whether one generated mesh is better than another. Practitioners commonly rely o…
Neither Parallel Nor Sequential: How DiffusionGemma Actually Commits Tokens
Ali Asaria, Tony Salomone, Deep Gandhi
Open diffusion language models are marketed as parallel, non-autoregressive decoders, yet the order in which a shipped checkpoint actually commits its tokens is almost never measur…
Realizing Native INT8 Compute for Diffusion Transformers on Consumer GPUs: A Fused INT8 GEMM Kernel for Ideogram 4.0
Ali Asaria, Tony Salomone, Deep Gandhi
Post-training INT8 (W8A8) quantization of diffusion transformers is widely deployed as a speed optimization, yet on consumer Ampere GPUs it is frequently slower than the FP8 and NF…
Holding the FP8 Quality Ceiling at 8-Bit Weights and Activations: INT8 and GGUF Post-Training Quantization of Ideogram 4.0 for Consumer GPUs
Deep Gandhi, Ali Asaria, Tony Salomone
We study post-training quantization (PTQ) of Ideogram 4.0, a 9.3B flow-matching diffusion transformer (DiT) that realizes classifier-free guidance with two separate-weight copies o…
A Federated Approach for Hate Speech Detection
Jay Gala, Deep Gandhi, Jash Mehta +1
Hate speech detection has been the subject of high research attention, due to the scale of content created on social media. In spite of the attention and the sensitive nature of th…
A Federated Approach to Predicting Emojis in Hindi Tweets
Deep Gandhi, Jash Mehta, Nirali Parekh +3
The use of emojis affords a visual modality to, often private, textual communication. The task of predicting emojis however provides a challenge for machine learning as emoji use t…