Abhishek Mittal

abhimittal

AI & ML interests

None yet

Recent Activity

updated a Space about 15 hours ago

abhimittal/sentinel-llm

updated a Space about 21 hours ago

abhimittal/ai-steering

updated a Space 1 day ago

abhimittal/veritas-hallucination-reduction

View all activity

Organizations

updated a Space about 15 hours ago

SentinelLLM Safety & Alignment Harness

🛡

Jailbreak, bias & format guardrails for LLMs — live demo

updated a Space about 21 hours ago

AI Steering

🧭

Simulate AI steering: reasoning, context, guardrails, routing

updated 2 Spaces 1 day ago

VERITAS — Hallucination-Reduction RAG

🔬

Claim-verified RAG that measurably reduces hallucination

Swarm Parameter Server

🐝

Generate text samples from a distributed training model

updated a Space 8 days ago

Live Latent-Space Navigator

🧭

Walk a diffusion model's latent space in real time

published a Space 8 days ago

Live Latent-Space Navigator

🧭

Walk a diffusion model's latent space in real time

updated a Space 8 days ago

Agentic Skill-Composition Benchmark

⚖

Token cost of skill-based agents vs monolithic prompts

published a Space 8 days ago

Agentic Skill-Composition Benchmark

⚖

Token cost of skill-based agents vs monolithic prompts

updated a Space 8 days ago

Quantization Error Propagation Viewer

🔬

Explore quantization error across model layers

published a Space 8 days ago

Quantization Error Propagation Viewer

🔬

Explore quantization error across model layers

updated a Space 8 days ago

KV Cache Budget Simulator

📐

KV cache bytes, OOM walls, PagedAttention, Pareto frontier

published a Space 8 days ago

KV Cache Budget Simulator

📐

KV cache bytes, OOM walls, PagedAttention, Pareto frontier

updated a Space 8 days ago

Speculative Decoding Trace

🎯

Watch rejection sampling accept/reject every draft token

published a Space 8 days ago

Speculative Decoding Trace

🎯

Watch rejection sampling accept/reject every draft token

published a Space 21 days ago

SentinelLLM Safety & Alignment Harness

🛡

Jailbreak, bias & format guardrails for LLMs — live demo

published a Space 23 days ago

AI Steering

🧭

Simulate AI steering: reasoning, context, guardrails, routing

published a Space 24 days ago

VERITAS — Hallucination-Reduction RAG

🔬

Claim-verified RAG that measurably reduces hallucination

updated a Space 25 days ago

Caliper — LLM Measurement Lab

🔬

Adaptive IRT evals, bias-audited judging, contamination

published a Space 25 days ago

Caliper — LLM Measurement Lab

🔬

Adaptive IRT evals, bias-audited judging, contamination

published a Space 30 days ago

Swarm Parameter Server

🐝

Generate text samples from a distributed training model

Abhishek Mittal

AI & ML interests

Recent Activity

Organizations

abhimittal's activity

SentinelLLM Safety & Alignment Harness

AI Steering

VERITAS — Hallucination-Reduction RAG

Swarm Parameter Server

Live Latent-Space Navigator

Live Latent-Space Navigator

Agentic Skill-Composition Benchmark

Agentic Skill-Composition Benchmark

Quantization Error Propagation Viewer

Quantization Error Propagation Viewer

KV Cache Budget Simulator

KV Cache Budget Simulator

Speculative Decoding Trace

Speculative Decoding Trace

SentinelLLM Safety & Alignment Harness

AI Steering

VERITAS — Hallucination-Reduction RAG

Caliper — LLM Measurement Lab

Caliper — LLM Measurement Lab

Swarm Parameter Server