arXiv Machine Learning
Jul 31
Subtract or Replay? Exact Deletion from Language-Model Memory
arXiv:2607. 27539v1 Announce Type: new Abstract: Exact deletion from persistent language-model memory depends on how that memory represents a record.
Exact Record Omission in Delta Attention: A Transport Criterion, Its Cost, and a Replay Certificate
Related stories
arXiv Machine Learning
Aug 14
Subtract, Transport, or Replay? Auditable Deletion from Language-Model Memory
arXiv:2607. 27539v2 Announce Type: replace Abstract: Exact deletion from persistent language-model memory depends on whether a record's effect remains addressable after later computation.
arXiv Machine Learning
5d ago
Can an AI Assistant Really Forget? Auditable Deletion from Addressable Memory
This paper introduces a deletion interface for a pretrained language model, measuring how effectively deleted records are removed from the model’s memory. By retrofitting a support‑vector memory gate into the global attention layers of a frozen Gemma 3, the authors show that deletions can be performed without altering weights and that the resulting state is close to a reference state that never stored the record. Experiments on 4B‑parameter models demonstrate low perplexity impact and strong evidence that deleted content is hard to recover, while larger or smaller models fail to achieve the same guarantees.
arXiv AI
Sep 7
Forgetting Without Restarting: Execution-State Unlearning for Stateful LLM Agents
arXiv:2609. 04875v1 Announce Type: cross Abstract: Long-running LLM agents are stateful: beyond the transcript they accrete compressed summaries, plaintext memory, pending tool plans, and, under every serving API, a KV cache.
arXiv Machine Learning
Jul 15
Forgetful Attention: A Trainable Support-Vector Memory with Certified Selection and Exact Unlearning
arXiv:2607. 12204v1 Announce Type: new Abstract: Attention can be viewed as an online learner over context, yet existing test-time memories cannot certify that dropping a token leaves outputs unchanged or delete its influence outright.
arXiv Machine Learning
Sep 1
Kathleen Remembers: Length-Invariant One-Shot Recall Without Attention
arXiv:2608.30376v1 Announce Type: cross Abstract: Recurrent, attention-free sequence models share a structural weakness: a fading state cannot perform exact recall of something seen once, far in the...
Hugging Face Trending Papers
Jun 24
Reclaim Evaluation: A Lossy Memory Is Worse Than an Empty One
A language model's memory can be worse than having no memory at all. Give a model a memory that kept a wrong conclusion but dropped the work behind it, and it emits that stale value as a confident answer; give the same model an empty memory and it abstains.
arXiv Machine Learning
Aug 6
Forgetful Attention: An Auditable Support-Vector Memory for Selective Retention and Verified Deletion
arXiv:2607. 12204v2 Announce Type: replace Abstract: Auditable memory requires a precise contract: which output is preserved, relative to which reference solve, and across which updates.
arXiv AI
Jul 28
Eviction as Estimation: A Fixed-Lag Smoothing View of Test-Time Memory, and When Measuring Beats Accumulating
arXiv:2607. 24667v1 Announce Type: new Abstract: A language model with a bounded working memory must repeatedly decide which stored items to keep.
arXiv Machine Learning
Sep 1
Ceiling-Clipped Acceptance Histograms Indicate Stranded Speed-up in Block-Diffusion Speculative Decoding
arXiv:2608.30427v1 Announce Type: cross Abstract: Speculative decoding speeds up generation with an efficient draft model (drafter) that proposes tokens for a target model to verify in one pass, pres...
arXiv Computation and Language
Aug 28
TwinKV: A Composable Repair Pass for KV Cache Eviction via Pairwise Key Redundancy
TwinKV is a training‑free, attention‑free repair pass that identifies and swaps orphaned and redundant tokens in a KV cache, improving long‑context inference for small models. It works by detecting near‑duplicate keys and can be composed with existing eviction policies without altering their scoring rules. Experiments on Qwen3‑4B and Llama‑3.2‑1B across LongBench, LooGLE, RULER, and MMLU‑Pro show that TwinKV consistently improves performance for most configurations, especially at tighter compression ratios.
arXiv AI
Jul 28
Compute Globally, Materialize Locally: The Memory Contract of Sparse Event-KV
arXiv:2607. 23693v1 Announce Type: new Abstract: Long-horizon agents increasingly reuse their KV cache as memory: a serving system keeps a subset of cached entries and drops the rest.