Furiosa Algorithms Research
We work at the intersection of AI and hardware to make AI computing sustainable
RL Post-Training
Deploy the most capable models with strong latency and throughput.
Non-autoregressive Generation
Lower total cost of ownership with less energy, fewer racks, and air-cooled data centers of today.
Inference-time Algorithms
Stay future-proof for tomorrow’s models and transition with ease.
Publications
Scaling Test-Time Compute for DLLMs via Parallel Search
COLM
2026
Accepted
Workshop
diffusion-llm
search
parallel-decoding
View Job
Characterizing High Bandwidth Flash for LLM Serving
arXiv
2026
Published
kv-cache
long-context
View Job
AsyncOPD: How Stale Can On-Policy Distillation Be?
NeurIPS
2026
Accepted
Poster
reasoning
distillation
asynchronous-execution
View Job
EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts
NeurIPS
2026
Accepted
Poster
speculative-decoding
reinforcement-learning
rollout-generation
View Job
Transformers in the Dark: Navigating Unknown Search Spaces via Bandit Feedback
TMLR
2026
search
transformer
View Job
TABED: Test-Time Adaptive Ensemble Drafting for Robust Speculative Decoding in LVLMs
EACL
2026
speculative-decoding
vision-lanuage
View Job
LoSA: Locality Aware Sparse Attention for Block-Wise Diffusion Language Models
ICML
2026
diffusion-llm
long-context
sparse-attention
View Job
Draft-based Approximate Inference for LLMs
ICLR
2026
speculative-decoding
kv-cache
View Job
ParallelBench: Understanding the Tradeoffs of Parallel Decoding in Diffusion LLMs
ICLR
2026
parallel-decoding
benchmark
View Job
Inference-Aligned SFT for Diffusion LLMs via Group-based Trajectory Sampling
ICLR
2026
Workshop
diffusion-llm
discrete-diffusion
sft
View Job
XQuant: Breaking the Memory Wall for LLM Inference with KV Cache Rematerialization
2026
Preprint
kv-cache
quantization
View Job
Counting Guidance for High Fidelity Text-to-Image Synthesis
WACV
2025
text-to-image
diffusion
View Job
ReJump: A Tree-Jump Representation for Analyzing and Improving LLM Reasoning
ICML
2025
reasoning
search
interpretability
View Job
VersaPRM: Multi-Domain Process Reward Model via Synthetic Reasoning Data
ICML
2025
Oral
reward-model
reasoning
View Job
Parameter-Efficient Fine-Tuning of State Space Models
ICML
2025
ssm
peft
View Job
State-offset Tuning: State-based Parameter-Efficient Fine-Tuning for State Space Models
ACL
2025
ssm
peft
View Job
Eta Inversion: Designing an Optimal Eta Function for Diffusion-based Real Image Editing
ECCV
2024
diffusion
image-editing
View Job
Can MLLMs Perform Multimodal In-Context Learning for Text-to-Image Generation?
COLM
2024
text-to-image
in-context-learning
View Job
Long-term collaboration partners on LLM efficiency, quantization, parallel decoding, and other advanced research areas for efficient inference.
