hassenhamdi
hassenhamdi
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
2 days ago
KV-Distill: Nearly Lossless Learnable Context Compression for LLMs
upvoted
a
paper
2 days ago
LMCache: An Efficient KV Cache Layer for Enterprise-Scale LLM Inference
Organizations
Diffusion
MLLM
-
NextFlow: Unified Sequential Modeling Activates Multimodal Understanding and Generation
Paper • 2601.02204 • Published • 60 -
HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding
Paper • 2601.14724 • Published • 71 -
VIOLA: Towards Video In-Context Learning with Minimal Annotations
Paper • 2601.15549 • Published • 4
Agents
-
Imagine-then-Plan: Agent Learning from Adaptive Lookahead with World Models
Paper • 2601.08955 • Published • 13 -
EvoFSM: Controllable Self-Evolution for Deep Research with Finite State Machines
Paper • 2601.09465 • Published • 40 -
MAXS: Meta-Adaptive Exploration with LLM Agents
Paper • 2601.09259 • Published • 94 -
Toward Efficient Agents: Memory, Tool learning, and Planning
Paper • 2601.14192 • Published • 49
LLM
-
A Safety Report on GPT-5.2, Gemini 3 Pro, Qwen3-VL, Doubao 1.8, Grok 4.1 Fast, Nano Banana Pro, and Seedream 4.5
Paper • 2601.10527 • Published • 24 -
PACEvolve: Enabling Long-Horizon Progress-Aware Consistent Evolution
Paper • 2601.10657 • Published • 20 -
TranslateGemma Technical Report
Paper • 2601.09012 • Published • 19 -
Recursive Language Models
Paper • 2512.24601 • Published • 77
RAG
-
From RAG to Memory: Non-Parametric Continual Learning for Large Language Models
Paper • 2502.14802 • Published • 13 -
EvoFSM: Controllable Self-Evolution for Deep Research with Finite State Machines
Paper • 2601.09465 • Published • 40 -
Parallel Context-of-Experts Decoding for Retrieval Augmented Generation
Paper • 2601.08670 • Published • 19
Training-Free
Optimization
-
MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head
Paper • 2601.07832 • Published • 51 -
Towards Automated Kernel Generation in the Era of LLMs
Paper • 2601.15727 • Published • 16 -
HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding
Paper • 2601.14724 • Published • 71
Video generation
Algorithmic Evolution
-
PACEvolve: Enabling Long-Horizon Progress-Aware Consistent Evolution
Paper • 2601.10657 • Published • 20 -
Controlled Self-Evolution for Algorithmic Code Optimization
Paper • 2601.07348 • Published • 112 -
LoongFlow: Directed Evolutionary Search via a Cognitive Plan-Execute-Summarize Paradigm
Paper • 2512.24077 • Published • 4
Papers
Coding
Training-Free
Diffusion
Optimization
-
MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head
Paper • 2601.07832 • Published • 51 -
Towards Automated Kernel Generation in the Era of LLMs
Paper • 2601.15727 • Published • 16 -
HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding
Paper • 2601.14724 • Published • 71
MLLM
-
NextFlow: Unified Sequential Modeling Activates Multimodal Understanding and Generation
Paper • 2601.02204 • Published • 60 -
HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding
Paper • 2601.14724 • Published • 71 -
VIOLA: Towards Video In-Context Learning with Minimal Annotations
Paper • 2601.15549 • Published • 4
Video generation
Agents
-
Imagine-then-Plan: Agent Learning from Adaptive Lookahead with World Models
Paper • 2601.08955 • Published • 13 -
EvoFSM: Controllable Self-Evolution for Deep Research with Finite State Machines
Paper • 2601.09465 • Published • 40 -
MAXS: Meta-Adaptive Exploration with LLM Agents
Paper • 2601.09259 • Published • 94 -
Toward Efficient Agents: Memory, Tool learning, and Planning
Paper • 2601.14192 • Published • 49
Algorithmic Evolution
-
PACEvolve: Enabling Long-Horizon Progress-Aware Consistent Evolution
Paper • 2601.10657 • Published • 20 -
Controlled Self-Evolution for Algorithmic Code Optimization
Paper • 2601.07348 • Published • 112 -
LoongFlow: Directed Evolutionary Search via a Cognitive Plan-Execute-Summarize Paradigm
Paper • 2512.24077 • Published • 4
LLM
-
A Safety Report on GPT-5.2, Gemini 3 Pro, Qwen3-VL, Doubao 1.8, Grok 4.1 Fast, Nano Banana Pro, and Seedream 4.5
Paper • 2601.10527 • Published • 24 -
PACEvolve: Enabling Long-Horizon Progress-Aware Consistent Evolution
Paper • 2601.10657 • Published • 20 -
TranslateGemma Technical Report
Paper • 2601.09012 • Published • 19 -
Recursive Language Models
Paper • 2512.24601 • Published • 77
Papers
RAG
-
From RAG to Memory: Non-Parametric Continual Learning for Large Language Models
Paper • 2502.14802 • Published • 13 -
EvoFSM: Controllable Self-Evolution for Deep Research with Finite State Machines
Paper • 2601.09465 • Published • 40 -
Parallel Context-of-Experts Decoding for Retrieval Augmented Generation
Paper • 2601.08670 • Published • 19