Add pipeline tag, remove arxiv tag from metadata

#1
by nielsr HF Staff - opened
Files changed (1) hide show
  1. README.md +5 -5
README.md CHANGED
@@ -1,8 +1,8 @@
1
  ---
2
- license: apache-2.0
3
  library_name: pytorch
 
 
4
  tags:
5
- - arxiv:2611.15315
6
  - agent-memory
7
  - long-term-memory
8
  - persistent-memory
@@ -16,7 +16,7 @@ tags:
16
 
17
  MIGRO is a decoupled long-term memory system that stores experience in a persistent state, allowing successive language models to read inherited observations and continue writing.
18
 
19
- [Paper](https://arxiv.org/abs/2611.15315) · [Code](https://github.com/zOUMINGXI/MIGRO) · [Interactive demo](https://zoumingxi.github.io/MIGRO/) · [Runtime guide](https://github.com/zOUMINGXI/MIGRO/blob/main/docs/runtime.md)
20
 
21
  ## Released components
22
 
@@ -76,7 +76,7 @@ The [demo guide](https://github.com/zOUMINGXI/MIGRO/blob/main/demo/README.md) de
76
 
77
  These resources support MIGRO memory construction, persistence, host-interface reading and continued writing. Answer generation combines them with an external host language model and the runtime's retrieval components.
78
 
79
- The [technical report](https://arxiv.org/abs/2611.15315) evaluates the complete system on long-term question answering, cross-host transfer and persistent storage. [Evaluation details](https://github.com/zOUMINGXI/MIGRO/blob/main/docs/evaluation.md) describe the settings, cohorts and baseline operations. Deployment behavior depends on the selected host, interface and retrieval budget.
80
 
81
  Host-interface weights are specific to their supported host configurations. The [runtime guide](https://github.com/zOUMINGXI/MIGRO/blob/main/docs/runtime.md) specifies required models and dependencies.
82
 
@@ -101,4 +101,4 @@ See LICENSE, NOTICE, THIRD_PARTY_NOTICES.md and PROVENANCE.json for the existing
101
  primaryClass = {cs.AI},
102
  url = {https://arxiv.org/abs/2611.15315}
103
  }
104
- ~~~
 
1
  ---
 
2
  library_name: pytorch
3
+ license: apache-2.0
4
+ pipeline_tag: text-retrieval
5
  tags:
 
6
  - agent-memory
7
  - long-term-memory
8
  - persistent-memory
 
16
 
17
  MIGRO is a decoupled long-term memory system that stores experience in a persistent state, allowing successive language models to read inherited observations and continue writing.
18
 
19
+ [Paper](https://huggingface.co/papers/2611.15315) · [Code](https://github.com/zOUMINGXI/MIGRO) · [Interactive demo](https://zoumingxi.github.io/MIGRO/) · [Runtime guide](https://github.com/zOUMINGXI/MIGRO/blob/main/docs/runtime.md)
20
 
21
  ## Released components
22
 
 
76
 
77
  These resources support MIGRO memory construction, persistence, host-interface reading and continued writing. Answer generation combines them with an external host language model and the runtime's retrieval components.
78
 
79
+ The [technical report](https://huggingface.co/papers/2611.15315) evaluates the complete system on long-term question answering, cross-host transfer and persistent storage. [Evaluation details](https://github.com/zOUMINGXI/MIGRO/blob/main/docs/evaluation.md) describe the settings, cohorts and baseline operations. Deployment behavior depends on the selected host, interface and retrieval budget.
80
 
81
  Host-interface weights are specific to their supported host configurations. The [runtime guide](https://github.com/zOUMINGXI/MIGRO/blob/main/docs/runtime.md) specifies required models and dependencies.
82
 
 
101
  primaryClass = {cs.AI},
102
  url = {https://arxiv.org/abs/2611.15315}
103
  }
104
+ ~~~