Fields · AI · updated 54m ago

Inference & serving

Making models fast and cheap to run: serving systems, kernels, KV-cache, speculative decoding, hardware.

252papers this week−17.1% vs last week

All papers · 1.5k With code · 59

Newest Most relevant

1.4k papers this month

Papers

Inference & serving · ByteTrail

Fields · AI · updated 54m ago

Inference & serving

Making models fast and cheap to run: serving systems, kernels, KV-cache, speculative decoding, hardware.

252papers this week−17.1% vs last week

All papers · 1.5k With code · 59

Newest Most relevant

1.4k papers this month

Recent papers

All in Research →

arXiv cs.CLOct 19
Hierarchical Token Merging with Recursive Autoencoders for Unsupervised Grammar Induction
Murat Guney Kemal, Robert Lieck
Hierarchical abstraction is a fundamental principle across many data modalities, enabling complex sequences to be represented compositionally at multiple levels. Learning such hierarchies directly from data, without explicit structural supervision, remains a central challenge in representation learning. We investigate whether meaningful hierarchical structure can emerge from compression alone. While autoencoders learn compressed representations through reconstruction, this objective does not necessarily favour meaningful compositional structure. We study this challenge through unsupervised grammar induction, where the underlying hierarchy can be evaluated explicitly. We introduce a hierarchical token-merging autoencoder that recursively combines adjacent tokens into increasingly abstract representations, compressing entire sequences through a variational information bottleneck. The model jointly learns representations and hierarchical structure by marginalising over possible binary trees using dynamic programming. To address training instability, we combine independently trained models through unsupervised consensus and distillation. Experiments on a synthetic, ambiguous grammar…
PDF arXiv
arXiv cs.LGOct 19
Parallel Language Models via Variational Decoding
Felix Draxler, Robin C. Geyer, Daniel Geyfman, Farrin Marouf Sofian, Justus Will +11
Autoregressive language models emit one token per forward pass. This causes high inference latency, in particular as models are scaled up for quality. In this paper, we introduce Parallel Language Models (PLMs), which generate mutually consistent tokens in one forward pass by routing dependencies through latent auxiliary variables. PLMs are trained using a variational bound that reduces to an autoregressive loss plus a parallel decoding loss. Empirically, PLMs are on a faster and better Pareto frontier than autoregressive and discrete diffusion baselines. Pretrained PLMs achieve near-autoregressive pretraining loss on model scales of 80M to 3B parameters, and speedup follows a power law in model size. When post-trained, our 1.3B model matches or exceeds an identically trained autoregressive model on math, coding, and instruction-following benchmarks, speeding up inference $2.3\text{-}5.7\times$. Together, we show that parallel generation can be trained from a single training objective at autoregressive quality. We will make our code available at https://github.com/mandt-lab/plm.
PDF arXiv
arXiv cs.CLOct 19
BERT Is Already a Denoiser: Cheaply Unlocking Iterative Generation in Masked Language Models
Julio C. Amador Diaz Lopez
Masked language models (MLMs) such as BERT are typically used for representation learning despite their denoising pretraining. We test whether this capability supports conditional generation without diffusion training. Our decoder repeatedly predicts masked tokens and commits high-confidence predictions using a cosine schedule. It requires no diffusion timestep or reverse-diffusion objective. Frozen BERT already exhibits substantial denoising capability, reconstructing 61.0%, 37.5%, and 24.4% of masked tokens at 15%, 45%, and 60% corruption, respectively, although generation deteriorates sharply as visible context disappears. This capability alone does not yield task-directed generation: frozen BERT reaches only 11.0% on ARC-Easy and 4.2% on MMLU. Ordinary MLM adaptation, however, rapidly converts the same architecture into a usable generator. Full adaptation reaches 28.2% and 24.6%, respectively, while parameter-efficient adaptation substantially reduces unmatched outputs. On open-ended conditional generation, full MLM adaptation reaches BLEU/ROUGE-L of 0.163/0.583 on QQP and 0.107/0.327 on Quasar-T, placing it in the same broad performance range as published BERT models trained…
PDF arXiv
arXiv cs.AIOct 19
BetaMem: Learning to Remember a Changing World for Embodied Agents
Mai Liu, He Sun, Siru Zhong, Kerun Chen, Hao Yan +3
Long-horizon embodied agents face temporal confusion and incomplete or distorted records, recurring errors from fixed memory rules, and growing storage and retrieval costs. We present BetaMem, a framework for building and evolving traceable long-term memory through six linked layers: working, spatial, entity, episodic, experiential, and procedural memory. A dual-level write contract constrains operation executability and source support for content: supervised fine-tuning learns compliant memory operations, while reinforcement learning combines repeated sampling with teacher verification of the original observations to reward complete, accurate records and penalize omissions, distortion, and unsupported content. We formulate failure-driven policy recursive self-improvement through diagnosis along the causal sequence of memory operations and local rule repairs gated by independent replay. Atomic tools frame storage, updates, retrieval, and forgetting as cost-utility allocation under storage and read budgets. Using the open-source Qwen3.5-9B model for memory generation, BetaMem achieves overall scores of 48.08% on M3-Bench-robot, 92.08% on LoCoMo, 72.6% on OpenEQA EM-EQA, and 62.4%…
PDF arXiv
arXiv cs.AIOct 19
Breaking Diffusion: Parallel Reasoning with Draft Refinement
Jaesang Yu, Seoyeon Byun, Yun Wang, Yan Lu, Juho Kim
Drafting an answer allows a reasoning model to reconsider each decision in the context of the others. Yet repeated diffusion denoising does not ensure that individually plausible token updates form a better answer together. We introduce Draft Refinement Language Models (DRLMs), which use a single denoiser to propose parallel revisions and evaluate a candidate draft. We train the denoiser to reconstruct every token from uniformly corrupted drafts, teaching both preservation and repair. Its predictions specify revisions directly, without a diffusion reverse transition. Evaluation requires a different use of these predictions: confidence in an existing token reflects both contextual support and evidence from observing the token itself. Using the known corruption process, we correct for this self-token evidence to estimate how well each token is supported by the prompt and the remaining draft. Aggregating these estimates yields a cavity energy computed in one forward pass, without an additional scoring model. Each round proposes a revision, reads the completed candidate in its revised context, and retains it only if its energy is lower. Across Countdown, Sudoku-Extreme, and…
PDF arXiv
arXiv cs.CLOct 19
ReAnchor: Reusing Rejected Verifier States for Diffusion Drafting
Sanghyun Lee, Wonjin Nam, Seungho Jang, Jaeho Lee, Jiho Park +2
Block diffusion drafters accelerate speculative decoding by generating multiple draft tokens in a single forward pass. However, each pass produces only a fixed-length block from a single target-generated anchor, limiting how far the draft can extend. Meanwhile, target verification computes hidden states even at positions beyond the first rejection, but these states are typically discarded rather than reused. We propose ReAnchor, a training-free method that reanchors a pretrained drafter at shifted positions using discarded verifier states to generate parallel draft blocks. These blocks improve predictions within the original block and extend coverage beyond its endpoint. At sampling temperature of T=0, ReAnchor achieves its largest average gains on Gemma 4-12B, improving acceptance length by 19.4% and decoding speed by 17.9% across eight benchmarks. Averaged equally over four target models and eight benchmarks, it improves acceptance length by 15.2% and decoding speed by 13.4% with pretrained DFlash drafters.
PDF arXiv

Papers

Top tools here

Coming with more sources: stars history

All tools

NVIDIA Dynamo+60% downloads · 15.8k/wk+60.0%
BentoML+30% downloads · 41k/wk+29.7%
MLX+26% downloads · 342.6k/wk+25.5%
Open WebUI3 releases this week
mlx-lm+8% downloads · 140.9k/wk+7.5%

Open problems in Inference & serving

Efficient long-horizon context management3 papers raise it · 3 address it
Long-horizon agents need to retain and use relevant information without exceeding finite context windows.
- REMORY: Learning Residual Memory for Context Compactionraises · addresses
- Pack Light, CarryOn: Building Object-Oriented Context for Long-Horizon Agentsraises · addresses
- MemT-1.0: Towards Memory-Native Evolutionraises · addresses
Token-level LLM routing efficiency1 paper raises it · 1 addresses it
Fine-grained token-level routing improves cost-quality trade-offs but strains existing serving systems.
- TokenRouter: Efficient Serving System for Token-Level LLM Routingraises · addresses
Memory-induced sycophancy in agents1 paper raises it · 1 addresses it
Persistent memories can cause agents to over-align with user beliefs, even when they are incorrect or outdated.
- Memadapter: Counterfactual Adaptation Against Memory-induced Sycophancyraises · addresses
Quality gap in parallel token generation2 papers raise it · 2 address it
Diffusion language models generate tokens in parallel but lag behind autoregressive models in quality.
- ALoDLM: Adaptively Looped Diffusion Language Modelsraises · addresses
- Pivot-SD: Efficient Self-Distillation for Masked Diffusion Language Modelsraises · addresses
Sparse attention computation overhead1 paper raises it · 1 addresses it
Sparse attention reduces computation but still requires scoring all keys, limiting efficiency gains.
- DoSA: Dots Sparse Attentionraises · addresses

Named by an AI from these papers' abstracts.

Recently funded

Market

EMode PhotonixPre-seed · Oct 16$1M
MueonSeries A · Oct 15$65M
TrimagnetixSeed · Oct 15$1M
ModalSeries B+ · Oct 14$750M
Salience LabsSeries B+ · Oct 14$125M

Topics in this field

agent memory · memory construction · term memory248 papers53 this week
gpus · gpu · throughput212 papers32 this week
diffusion language models · language models diffusion · models diffusion language145 papers29 this week
sparse attention · linear attention · attention layers131 papers23 this week
continual learning · catastrophic forgetting · forgetting230 papers21 this week
aware routing · model routing · model llm routing82 papers20 this week

Active contributors

Activity

Recent papers

All in Research →

arXiv cs.CLOct 19
Hierarchical Token Merging with Recursive Autoencoders for Unsupervised Grammar Induction
Murat Guney Kemal, Robert Lieck
Hierarchical abstraction is a fundamental principle across many data modalities, enabling complex sequences to be represented compositionally at multiple levels. Learning such hierarchies directly from data, without explicit structural supervision, remains a central challenge in representation learning. We investigate whether meaningful hierarchical structure can emerge from compression alone. While autoencoders learn compressed representations through reconstruction, this objective does not necessarily favour meaningful compositional structure. We study this challenge through unsupervised grammar induction, where the underlying hierarchy can be evaluated explicitly. We introduce a hierarchical token-merging autoencoder that recursively combines adjacent tokens into increasingly abstract representations, compressing entire sequences through a variational information bottleneck. The model jointly learns representations and hierarchical structure by marginalising over possible binary trees using dynamic programming. To address training instability, we combine independently trained models through unsupervised consensus and distillation. Experiments on a synthetic, ambiguous grammar…
PDF arXiv
arXiv cs.LGOct 19
Parallel Language Models via Variational Decoding
Felix Draxler, Robin C. Geyer, Daniel Geyfman, Farrin Marouf Sofian, Justus Will +11
Autoregressive language models emit one token per forward pass. This causes high inference latency, in particular as models are scaled up for quality. In this paper, we introduce Parallel Language Models (PLMs), which generate mutually consistent tokens in one forward pass by routing dependencies through latent auxiliary variables. PLMs are trained using a variational bound that reduces to an autoregressive loss plus a parallel decoding loss. Empirically, PLMs are on a faster and better Pareto frontier than autoregressive and discrete diffusion baselines. Pretrained PLMs achieve near-autoregressive pretraining loss on model scales of 80M to 3B parameters, and speedup follows a power law in model size. When post-trained, our 1.3B model matches or exceeds an identically trained autoregressive model on math, coding, and instruction-following benchmarks, speeding up inference $2.3\text{-}5.7\times$. Together, we show that parallel generation can be trained from a single training objective at autoregressive quality. We will make our code available at https://github.com/mandt-lab/plm.
PDF arXiv
arXiv cs.CLOct 19
BERT Is Already a Denoiser: Cheaply Unlocking Iterative Generation in Masked Language Models
Julio C. Amador Diaz Lopez
Masked language models (MLMs) such as BERT are typically used for representation learning despite their denoising pretraining. We test whether this capability supports conditional generation without diffusion training. Our decoder repeatedly predicts masked tokens and commits high-confidence predictions using a cosine schedule. It requires no diffusion timestep or reverse-diffusion objective. Frozen BERT already exhibits substantial denoising capability, reconstructing 61.0%, 37.5%, and 24.4% of masked tokens at 15%, 45%, and 60% corruption, respectively, although generation deteriorates sharply as visible context disappears. This capability alone does not yield task-directed generation: frozen BERT reaches only 11.0% on ARC-Easy and 4.2% on MMLU. Ordinary MLM adaptation, however, rapidly converts the same architecture into a usable generator. Full adaptation reaches 28.2% and 24.6%, respectively, while parameter-efficient adaptation substantially reduces unmatched outputs. On open-ended conditional generation, full MLM adaptation reaches BLEU/ROUGE-L of 0.163/0.583 on QQP and 0.107/0.327 on Quasar-T, placing it in the same broad performance range as published BERT models trained…
PDF arXiv
arXiv cs.AIOct 19
BetaMem: Learning to Remember a Changing World for Embodied Agents
Mai Liu, He Sun, Siru Zhong, Kerun Chen, Hao Yan +3
Long-horizon embodied agents face temporal confusion and incomplete or distorted records, recurring errors from fixed memory rules, and growing storage and retrieval costs. We present BetaMem, a framework for building and evolving traceable long-term memory through six linked layers: working, spatial, entity, episodic, experiential, and procedural memory. A dual-level write contract constrains operation executability and source support for content: supervised fine-tuning learns compliant memory operations, while reinforcement learning combines repeated sampling with teacher verification of the original observations to reward complete, accurate records and penalize omissions, distortion, and unsupported content. We formulate failure-driven policy recursive self-improvement through diagnosis along the causal sequence of memory operations and local rule repairs gated by independent replay. Atomic tools frame storage, updates, retrieval, and forgetting as cost-utility allocation under storage and read budgets. Using the open-source Qwen3.5-9B model for memory generation, BetaMem achieves overall scores of 48.08% on M3-Bench-robot, 92.08% on LoCoMo, 72.6% on OpenEQA EM-EQA, and 62.4%…
PDF arXiv
arXiv cs.AIOct 19
Breaking Diffusion: Parallel Reasoning with Draft Refinement
Jaesang Yu, Seoyeon Byun, Yun Wang, Yan Lu, Juho Kim
Drafting an answer allows a reasoning model to reconsider each decision in the context of the others. Yet repeated diffusion denoising does not ensure that individually plausible token updates form a better answer together. We introduce Draft Refinement Language Models (DRLMs), which use a single denoiser to propose parallel revisions and evaluate a candidate draft. We train the denoiser to reconstruct every token from uniformly corrupted drafts, teaching both preservation and repair. Its predictions specify revisions directly, without a diffusion reverse transition. Evaluation requires a different use of these predictions: confidence in an existing token reflects both contextual support and evidence from observing the token itself. Using the known corruption process, we correct for this self-token evidence to estimate how well each token is supported by the prompt and the remaining draft. Aggregating these estimates yields a cavity energy computed in one forward pass, without an additional scoring model. Each round proposes a revision, reads the completed candidate in its revised context, and retains it only if its energy is lower. Across Countdown, Sudoku-Extreme, and…
PDF arXiv
arXiv cs.CLOct 19
ReAnchor: Reusing Rejected Verifier States for Diffusion Drafting
Sanghyun Lee, Wonjin Nam, Seungho Jang, Jaeho Lee, Jiho Park +2
Block diffusion drafters accelerate speculative decoding by generating multiple draft tokens in a single forward pass. However, each pass produces only a fixed-length block from a single target-generated anchor, limiting how far the draft can extend. Meanwhile, target verification computes hidden states even at positions beyond the first rejection, but these states are typically discarded rather than reused. We propose ReAnchor, a training-free method that reanchors a pretrained drafter at shifted positions using discarded verifier states to generate parallel draft blocks. These blocks improve predictions within the original block and extend coverage beyond its endpoint. At sampling temperature of T=0, ReAnchor achieves its largest average gains on Gemma 4-12B, improving acceptance length by 19.4% and decoding speed by 17.9% across eight benchmarks. Averaged equally over four target models and eight benchmarks, it improves acceptance length by 15.2% and decoding speed by 13.4% with pretrained DFlash drafters.
PDF arXiv

Inference & serving

Papers

Inference & serving

Recent papers

Hierarchical Token Merging with Recursive Autoencoders for Unsupervised Grammar Induction

Parallel Language Models via Variational Decoding

BERT Is Already a Denoiser: Cheaply Unlocking Iterative Generation in Masked Language Models

BetaMem: Learning to Remember a Changing World for Embodied Agents

Breaking Diffusion: Parallel Reasoning with Draft Refinement

ReAnchor: Reusing Rejected Verifier States for Diffusion Drafting

Papers

Top tools here

Open problems in Inference & serving

Recently funded

Topics in this field

Active contributors · 90 days

Active contributors

Activity · 12 weeks

Activity

Active contributors · 90 days

Activity · 12 weeks

Recent papers

Hierarchical Token Merging with Recursive Autoencoders for Unsupervised Grammar Induction

Parallel Language Models via Variational Decoding

BERT Is Already a Denoiser: Cheaply Unlocking Iterative Generation in Masked Language Models

BetaMem: Learning to Remember a Changing World for Embodied Agents

Breaking Diffusion: Parallel Reasoning with Draft Refinement

ReAnchor: Reusing Rejected Verifier States for Diffusion Drafting